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

    Neuronpedia

    INDEX
    Explanations

    movie descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Finally
    -0.06
     부탁
    -0.06
    653
    -0.06
     نص
    -0.06
    SizePolicy
    -0.06
     maturity
    -0.06
    ăm
    -0.06
     Formatting
    -0.06
    breaking
    -0.06
    blk
    -0.06
    POSITIVE LOGITS
     parchment
    0.07
     garage
    0.07
    (Response
    0.06
     depois
    0.06
     tournament
    0.06
     hobby
    0.06
    确定
    0.06
    /base
    0.06
     sexuales
    0.06
     Tipo
    0.06
    Act Density 0.010%

    No Known Activations