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

    Neuronpedia

    INDEX
    Explanations

    0,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Podesta
    -0.07
    قی
    -0.07
    conversion
    -0.06
    ones
    -0.06
    STANCE
    -0.06
     bite
    -0.06
    Incorrect
    -0.06
     vampire
    -0.06
    exus
    -0.06
    _fatal
    -0.06
    POSITIVE LOGITS
     अपर
    0.07
    刷
    0.07
    ち
    0.06
     Зам
    0.06
     avere
    0.06
     Ül
    0.06
    мос
    0.06
    .FileWriter
    0.06
    .Pay
    0.06
     Vinyl
    0.06
    Act Density 0.003%

    No Known Activations