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

    Neuronpedia

    INDEX
    Explanations

    Default deny

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recognizable
    -0.09
    ണക്ക
    -0.08
    IMPORTANT
    -0.08
    ണ
    -0.08
     담당
    -0.08
    human
    -0.08
    وند
    -0.08
     dik
    -0.08
    uman
    -0.07
    \Schema
    -0.07
    POSITIVE LOGITS
     positivo
    0.08
    yez
    0.08
    -ja
    0.08
    -positive
    0.08
     voto
    0.08
     yima
    0.08
    (children
    0.07
     الطبيعي
    0.07
    _positive
    0.07
    _Default
    0.07
    Act Density 0.002%

    No Known Activations