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

    Neuronpedia

    INDEX
    Explanations

    paper introductions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ερο
    -0.06
    kami
    -0.06
    �u
    -0.06
     😉
    -0.06
     married
    -0.06
    micro
    -0.06
    memo
    -0.06
    nio
    -0.06
     ürün
    -0.06
     безопасности
    -0.06
    POSITIVE LOGITS
    .Bot
    0.07
    .terminate
    0.06
     компон
    0.06
     gorge
    0.06
    .stub
    0.06
    Browse
    0.06
     permissions
    0.06
    .cluster
    0.06
    (':')[
    0.06
    .Symbol
    0.06
    Act Density 0.042%

    No Known Activations