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

    Neuronpedia

    INDEX
    Explanations

    Autoscaling

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ray
    -0.07
    诨
    -0.07
    谧
    -0.07
    搛
    -0.07
    的比赛
    -0.07
     unfamiliar
    -0.07
    焓
    -0.06
     japanese
    -0.06
    维权
    -0.06
    嵎
    -0.06
    POSITIVE LOGITS
    马力
    0.08
    .product
    0.07
    动态
    0.07
     consisting
    0.07
     Grandma
    0.07
     timeStamp
    0.06
    filme
    0.06
    enerative
    0.06
    ,password
    0.06
     consisted
    0.06
    Act Density 0.006%

    No Known Activations