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

    Neuronpedia

    INDEX
    Explanations

    purpose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vastly
    -0.06
    ontrol
    -0.06
     MART
    -0.06
    ategorias
    -0.06
     тільки
    -0.06
     首
    -0.06
    gunta
    -0.06
    ứ
    -0.06
     Educational
    -0.06
    _INTEGER
    -0.06
    POSITIVE LOGITS
     ISO
    0.07
    �
    0.07
     fertility
    0.06
    .TextInput
    0.06
     بغ
    0.06
    >tag
    0.06
     ड
    0.06
    라피
    0.06
     Representatives
    0.06
     bub
    0.06
    Act Density 0.006%

    No Known Activations