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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TRAIN
    -0.07
    每一天
    -0.07
     自
    -0.07
    引き
    -0.06
     �
    -0.06
    �
    -0.06
    CLE
    -0.06
     �
    -0.06
     �
    -0.06
    powiedź
    -0.06
    POSITIVE LOGITS
    _dev
    0.07
    redient
    0.07
    地下水
    0.07
    erti
    0.07
    .IP
    0.07
    _Camera
    0.07
    .extensions
    0.07
    站
    0.07
     Kat
    0.06
    trusted
    0.06
    Act Density 0.030%

    No Known Activations