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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    casting
    -0.07
    Edit
    -0.07
     Pazar
    -0.07
    .Component
    -0.06
    forcing
    -0.06
    ί
    -0.06
    talk
    -0.06
    QWidget
    -0.06
    /tests
    -0.06
    mes
    -0.06
    POSITIVE LOGITS
     withdrawals
    0.08
     modern
    0.07
    ')</
    0.07
    erre
    0.07
     crowd
    0.07
     ()↵
    0.07
     cloud
    0.07
     Kadın
    0.06
     []↵
    0.06
     Continued
    0.06
    Act Density 0.004%

    No Known Activations