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

    Neuronpedia

    INDEX
    Explanations

    ic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     besides
    -0.07
     satisfying
    -0.06
    ensored
    -0.06
     killing
    -0.06
    (size
    -0.06
    茭
    -0.06
    枲
    -0.06
     Calif
    -0.06
     celle
    -0.06
    把持
    -0.06
    POSITIVE LOGITS
    ลง
    0.07
    Qty
    0.07
    _have
    0.07
    风湿
    0.07
    .='<
    0.07
    لق
    0.07
     Ła
    0.07
    LIBINT
    0.07
    SEQU
    0.07
    _recent
    0.07
    Act Density 0.001%

    No Known Activations