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

    Neuronpedia

    INDEX
    Explanations

    medications and treatments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     padded
    -0.08
     strengthen
    -0.08
     IMPLEMENT
    -0.07
    胁
    -0.07
    SR
    -0.07
    实施细则
    -0.07
    .addAction
    -0.07
    パー�
    -0.06
    .impl
    -0.06
    _PB
    -0.06
    POSITIVE LOGITS
     Dou
    0.07
    (camera
    0.07
     violently
    0.07
    إرسال
    0.06
    wor
    0.06
    赛车
    0.06
    דע
    0.06
    contres
    0.06
    Bubble
    0.06
     dumb
    0.06
    Act Density 0.011%

    No Known Activations