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

    Neuronpedia

    INDEX
    Explanations

    Statistics and rankings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Пів
    -0.07
     beer
    -0.06
    DAY
    -0.06
    .Source
    -0.06
    _enqueue
    -0.06
     bụ
    -0.06
    Day
    -0.06
    Ο
    -0.06
     difícil
    -0.06
     addon
    -0.06
    POSITIVE LOGITS
    .ReadString
    0.07
    貼
    0.07
    สมาช
    0.06
    anes
    0.06
    -Methods
    0.06
     furious
    0.06
    agos
    0.06
    \/\/
    0.06
    рис
    0.06
    mtime
    0.06
    Act Density 0.027%

    No Known Activations