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

    Neuronpedia

    INDEX
    Explanations

    private

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    確認
    -0.08
    _ALL
    -0.07
     Penny
    -0.07
    aton
    -0.07
    ellschaft
    -0.07
     갤
    -0.07
    _den
    -0.07
    vard
    -0.06
    akit
    -0.06
     resultat
    -0.06
    POSITIVE LOGITS
     temin
    0.07
     位
    0.06
    (docs
    0.06
     ㅇ
    0.06
     finance
    0.06
     authorities
    0.06
     bg
    0.06
    -token
    0.06
     bow
    0.06
    /grpc
    0.06
    Act Density 0.021%

    No Known Activations