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

    Neuronpedia

    INDEX
    Explanations

    \

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Message
    -0.07
     zipper
    -0.06
     Fucking
    -0.06
     мм
    -0.06
     challenge
    -0.06
    仁
    -0.06
     altına
    -0.06
    because
    -0.06
    ภาพ
    -0.06
    등학교
    -0.06
    POSITIVE LOGITS
    /window
    0.07
    _px
    0.07
    ตะว
    0.06
    _district
    0.06
    iPhone
    0.06
    hong
    0.06
    漫画
    0.06
    imagem
    0.06
    centers
    0.06
    ickle
    0.06
    Act Density 0.009%

    No Known Activations