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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    studies related to the efficacy and safety of medications for specific medical conditions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on numeric ratio or allocation expressions (e.g. “1:1” and similar numeric‐colon patterns).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    tolower
    -0.08
    later
    -0.07
    _available
    -0.07
     entirety
    -0.06
    -generic
    -0.06
    heid
    -0.06
    numbers
    -0.06
    prepared
    -0.06
    validation
    -0.06
    _registered
    -0.06
    POSITIVE LOGITS
    (IB
    0.06
     anne
    0.06
     popis
    0.06
    (sp
    0.06
     мо
    0.06
    <Cell
    0.06
    )>>
    0.06
     formulation
    0.06
     Gard
    0.05
    [url
    0.05
    Act Density 0.001%

    No Known Activations