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

    Neuronpedia

    INDEX
    Explanations

    tolerance

    np_max-act · gemini-2.0-flash

    The neuron specifically detects mentions of developing or building up a tolerance over time.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ’s
    -0.07
     знову
    -0.07
    yle
    -0.07
    /gpl
    -0.07
     give
    -0.06
     здат
    -0.06
    انگ
    -0.06
     actionTypes
    -0.06
     Kids
    -0.06
    INAL
    -0.06
    POSITIVE LOGITS
    759
    0.07
    ibbon
    0.06
    exp
    0.06
     crust
    0.06
    струк
    0.06
     frog
    0.06
    ระด
    0.06
     Fraser
    0.06
    :message
    0.06
    fol
    0.06
    Act Density 0.022%

    No Known Activations