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

    Neuronpedia

    INDEX
    Explanations

    require

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     başarılı
    -0.08
    Native
    -0.07
    ウ
    -0.07
    になれ
    -0.07
    ｼ
    -0.07
    .Async
    -0.07
    빰
    -0.07
     customary
    -0.06
    试试
    -0.06
    当事
    -0.06
    POSITIVE LOGITS
    ясн
    0.07
    ழ
    0.07
    rink
    0.07
    涿
    0.07
    כיכר
    0.07
    坑
    0.07
    uthor
    0.07
    (++
    0.07
    同情
    0.06
    isers
    0.06
    Act Density 0.004%

    No Known Activations