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

    Neuronpedia

    INDEX
    Explanations

    opensource

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /Getty
    -0.07
     Marriott
    -0.07
    ='${
    -0.06
     или
    -0.06
    494
    -0.06
     sarc
    -0.06
    /<
    -0.06
     Thor
    -0.06
    .date
    -0.06
    Thumbnail
    -0.06
    POSITIVE LOGITS
    aises
    0.07
    ime
    0.06
    ンズ
    0.06
    合わせ
    0.06
     Missile
    0.06
    INET
    0.06
    IMIZE
    0.06
     finale
    0.06
     رابط
    0.06
    AGAIN
    0.06
    Act Density 0.001%

    No Known Activations