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

    Neuronpedia

    INDEX
    Explanations

    liability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     센
    -0.07
    .getTable
    -0.07
    _DEFINED
    -0.06
    Fo
    -0.06
     き
    -0.06
     давно
    -0.06
     realizado
    -0.06
    ικών
    -0.06
    ıştır
    -0.06
     invoices
    -0.06
    POSITIVE LOGITS
     affect
    0.07
     discounted
    0.06
    response
    0.06
     max
    0.06
     stun
    0.06
    >m
    0.06
    CTIONS
    0.06
     graceful
    0.06
     accents
    0.06
     barring
    0.06
    Act Density 0.002%

    No Known Activations