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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﲡ
    -0.07
    泂
    -0.07
    .readline
    -0.07
     kite
    -0.07
    -Class
    -0.07
     himself
    -0.07
     IDENT
    -0.06
    ооруж
    -0.06
    _vi
    -0.06
     Bowie
    -0.06
    POSITIVE LOGITS
    ʜ
    0.07
     lå
    0.07
     pounded
    0.07
    swiper
    0.07
    木耳
    0.07
    活跃
    0.07
    英镑
    0.07
     früh
    0.06
     가능성
    0.06
    旅遊
    0.06
    Act Density 0.136%

    No Known Activations