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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     пут
    -0.07
     faulty
    -0.06
     estimating
    -0.06
     жінок
    -0.06
    $message
    -0.06
    _prepare
    -0.06
     EMP
    -0.06
    upakan
    -0.06
     Arabian
    -0.06
    ripsi
    -0.06
    POSITIVE LOGITS
    otine
    0.07
    atty
    0.07
     tailor
    0.07
    Nintendo
    0.07
     дос
    0.07
    ValueHandling
    0.06
     ""
    0.06
    unik
    0.06
    ёт
    0.06
    理
    0.06
    Act Density 0.002%

    No Known Activations