Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    side effects and safety

    np_max-act · gemini-2.0-flash

    The neuron fires on dosage, side‐effect, and precautionary language—i.e. mentions of “how much,” “if taken too much,” numeric dosing, risks, and warnings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    Mentions of safety, precautions, side effects, dosing, or interactions (warnings about supplements/medical risks).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     Standards
    -0.07
    [p
    -0.07
    VP
    -0.07
    inned
    -0.07
     tf
    -0.06
    -prop
    -0.06
    (tf
    -0.06
     terminate
    -0.06
     Vader
    -0.06
    (Float
    -0.06
    POSITIVE LOGITS
     helf
    0.07
     kita
    0.07
    AsString
    0.07
     inclusion
    0.06
    TableModel
    0.06
    ','=','
    0.06
     olmam
    0.06
     stř
    0.06
    ensem
    0.06
     fullPath
    0.06
    Act Density 0.030%

    No Known Activations