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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tutto
    -0.07
     todd
    -0.07
    格尔
    -0.07
    owany
    -0.07
    Qué
    -0.07
    听
    -0.07
    实体
    -0.06
     Tv
    -0.06
    tagName
    -0.06
     Mp
    -0.06
    POSITIVE LOGITS
    iasco
    0.07
    تحكم
    0.07
    พอใจ
    0.07
     disput
    0.07
     khuẩn
    0.06
    Priority
    0.06
    vla
    0.06
     dated
    0.06
     большим
    0.06
    最初
    0.06
    Act Density 0.033%

    No Known Activations