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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tết
    -0.07
    Tar
    -0.07
    .series
    -0.07
    طة
    -0.07
     месяцев
    -0.07
    ree
    -0.07
    RV
    -0.06
    ะ
    -0.06
    ftar
    -0.06
    sel
    -0.06
    POSITIVE LOGITS
    Replacement
    0.08
     куд
    0.08
    _family
    0.07
    更快
    0.07
    ProgressDialog
    0.07
    密码
    0.07
    �
    0.07
     rapide
    0.07
     스스
    0.07
     sluts
    0.07
    Act Density 0.006%

    No Known Activations