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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dense
    -0.08
    Ars
    -0.07
     Raf
    -0.06
     ens
    -0.06
    _mo
    -0.06
     Кур
    -0.06
     mon
    -0.06
     मद
    -0.06
     جم
    -0.06
     الس
    -0.06
    POSITIVE LOGITS
     oluştur
    0.07
     generally
    0.07
    CGFloat
    0.06
    region
    0.06
     relu
    0.06
    ]}↵
    0.06
     specializing
    0.06
    ейств
    0.06
    ساس
    0.06
     北
    0.06
    Act Density 0.000%

    No Known Activations