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

    Neuronpedia

    INDEX
    Explanations

    Rhetorical questions about ease

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    indow
    -0.07
    telephone
    -0.07
     insign
    -0.07
    tok
    -0.07
    ooth
    -0.07
    ﳫ
    -0.07
    станов
    -0.07
     Accum
    -0.07
    父子
    -0.07
    udev
    -0.06
    POSITIVE LOGITS
    ار
    0.07
    ividad
    0.06
    ирование
    0.06
    حرية
    0.06
    הפוך
    0.06
     chatte
    0.06
    RATE
    0.06
    致
    0.06
    ität
    0.06
    祝贺
    0.06
    Act Density 0.016%

    No Known Activations