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

    Neuronpedia

    INDEX
    Explanations

    location

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    즌
    -0.07
    多い
    -0.07
    _filt
    -0.07
     берем
    -0.07
    exc
    -0.07
     معد
    -0.07
    あ
    -0.07
    tparam
    -0.06
    ，不
    -0.06
     آزمون
    -0.06
    POSITIVE LOGITS
    Outside
    0.14
     inside
    0.12
     Outside
    0.11
    outside
    0.10
    Inside
    0.09
     Inside
    0.09
     outside
    0.08
     worst
    0.07
     Harvard
    0.07
    inside
    0.07
    Act Density 0.016%

    No Known Activations