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

    Neuronpedia

    INDEX
    Explanations

    technical/scientific documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    אזור
    -0.08
    重庆市
    -0.07
     degraded
    -0.07
     prin
    -0.07
    盉
    -0.07
    .Navigator
    -0.07
     seasoning
    -0.06
     الرجل
    -0.06
     дизайн
    -0.06
    レストラン
    -0.06
    POSITIVE LOGITS
     *(*
    0.08
    Length
    0.07
    *self
    0.07
    目に
    0.06
     scares
    0.06
     sends
    0.06
    靠近
    0.06
    とにか
    0.06
    骗
    0.06
    underscore
    0.06
    Act Density 0.044%

    No Known Activations