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

    Neuronpedia

    INDEX
    Explanations

    krak

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     urgently
    -0.07
     ké
    -0.07
    besch
    -0.07
    听力
    -0.07
    (alert
    -0.07
    ⓙ
    -0.07
     roc
    -0.06
    pré
    -0.06
    出色
    -0.06
    _alert
    -0.06
    POSITIVE LOGITS
    --↵
    0.08
     pracowników
    0.07
    MAL
    0.07
     deaths
    0.07
     brass
    0.07
    טווח
    0.07
    入股
    0.07
     RIP
    0.07
    -par
    0.06
    Marca
    0.06
    Act Density 0.001%

    No Known Activations