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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scala
    -0.07
    Christmas
    -0.07
    _points
    -0.06
    quan
    -0.06
     infinite
    -0.06
     deflect
    -0.06
    _stats
    -0.06
    Partial
    -0.06
    .toArray
    -0.06
     correlated
    -0.06
    POSITIVE LOGITS
     �
    0.07
    推薦
    0.07
    ensible
    0.06
    VIDEO
    0.06
     audi
    0.06
    เวอร
    0.06
     викон
    0.06
     ceremon
    0.06
     الذين
    0.06
     ph
    0.06
    Act Density 0.003%

    No Known Activations