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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >",
    -0.07
    868
    -0.07
    .DEFAULT
    -0.06
    "d
    -0.06
    $,
    -0.06
    步
    -0.06
    раст
    -0.06
     "@"
    -0.06
     ['.
    -0.06
    _QUERY
    -0.06
    POSITIVE LOGITS
    ABCDEFGHI
    0.07
     zou
    0.06
     Andre
    0.06
     messed
    0.06
    :::::|
    0.06
    部
    0.06
    iero
    0.06
     hikes
    0.06
     verificar
    0.06
     Mısır
    0.06
    Act Density 0.232%

    No Known Activations