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

    Neuronpedia

    INDEX
    Explanations

    yc or com

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    入手
    -0.08
    上线
    -0.08
    (StringUtils
    -0.07
    房间里
    -0.07
    .GetMapping
    -0.07
     comando
    -0.07
    _FILE
    -0.07
    座谈
    -0.07
    环境下
    -0.07
    KM
    -0.07
    POSITIVE LOGITS
     vant
    0.07
     الوز
    0.07
    เทคโนโล
    0.07
    ierung
    0.07
    �재
    0.07
    prit
    0.07
     prisoners
    0.06
     الرجال
    0.06
    .Area
    0.06
     Plate
    0.06
    Act Density 0.030%

    No Known Activations