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

    Neuronpedia

    INDEX
    Explanations

    9

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PAS
    -0.07
    opi
    -0.07
     vein
    -0.07
    命中
    -0.07
    _filled
    -0.07
    Expanded
    -0.07
    DY
    -0.06
    嗑
    -0.06
    代
    -0.06
    芦
    -0.06
    POSITIVE LOGITS
    的目标
    0.07
     aspirations
    0.07
     eğitim
    0.07
     batting
    0.07
    mıştır
    0.07
     projects
    0.07
     clients
    0.06
    スタッフ
    0.06
    Ƨ
    0.06
    /reset
    0.06
    Act Density 0.003%

    No Known Activations