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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oluştur
    -0.07
     prayed
    -0.07
    örü
    -0.07
     glued
    -0.07
     дальше
    -0.07
    技术支持
    -0.07
    🔙
    -0.07
    屋子
    -0.07
    真人
    -0.07
    (fin
    -0.07
    POSITIVE LOGITS
    who
    0.08
    международ
    0.07
     Carnegie
    0.07
     getenv
    0.07
    INV
    0.07
     рын
    0.07
     LAND
    0.07
    _active
    0.07
    _SH
    0.06
    ন
    0.06
    Act Density 0.001%

    No Known Activations