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

    Neuronpedia

    INDEX
    Explanations

    spy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    assium
    -0.08
    ">',↵
    -0.07
     of
    -0.07
    そうだ
    -0.07
    出し
    -0.07
    肯定是
    -0.07
    levard
    -0.07
    ellan
    -0.07
     Fallen
    -0.07
    .Code
    -0.07
    POSITIVE LOGITS
    ²
    0.07
    ₣
    0.07
    ɴ
    0.07
    ⁿ
    0.07
    ичество
    0.07
    Many
    0.07
    🕷
    0.06
    many
    0.06
     الحقوق
    0.06
    Ӫ
    0.06
    Act Density 0.003%

    No Known Activations