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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    然而
    -0.07
    业
    -0.07
     discussed
    -0.06
     ж
    -0.06
    امت
    -0.06
    pto
    -0.06
     adolescents
    -0.06
    CHANT
    -0.06
     dismissed
    -0.06
    apk
    -0.06
    POSITIVE LOGITS
    .SimpleDateFormat
    0.06
     dreaming
    0.06
    llib
    0.06
     Mort
    0.06
    .all
    0.06
    (tolua
    0.06
    (equalTo
    0.06
    が出
    0.05
     Sco
    0.05
     buddy
    0.05
    Act Density 0.042%

    No Known Activations