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

    Neuronpedia

    INDEX
    Explanations

    .length

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ifacts
    -0.06
     Secrets
    -0.06
     veri
    -0.06
     Principle
    -0.06
     Gamer
    -0.06
    String
    -0.06
     io
    -0.06
     Prometheus
    -0.06
    Supply
    -0.06
    ki
    -0.06
    POSITIVE LOGITS
    orea
    0.06
    چار
    0.06
    夢
    0.06
    roma
    0.06
    -choice
    0.06
     SOLD
    0.06
     friends
    0.06
     months
    0.06
     комплекс
    0.06
     종
    0.06
    Act Density 0.003%

    No Known Activations