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

    Neuronpedia

    INDEX
    Explanations

    close

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -thinking
    -0.07
     Diet
    -0.07
     Implementation
    -0.07
     projecting
    -0.07
    修改
    -0.06
     gelir
    -0.06
    _processing
    -0.06
     onAnimation
    -0.06
    halten
    -0.06
    III
    -0.06
    POSITIVE LOGITS
     друж
    0.07
     Zelda
    0.07
     外部リンク
    0.06
     üz
    0.06
     серь
    0.06
    ıştır
    0.06
     πρώ
    0.06
     facing
    0.06
    swagen
    0.06
    用品
    0.06
    Act Density 0.008%

    No Known Activations