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

    Neuronpedia

    INDEX
    Explanations

    snake

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     took
    -0.07
    yd
    -0.07
     Fraud
    -0.07
    -prev
    -0.07
    JPEG
    -0.07
    .prev
    -0.07
     Clips
    -0.07
    е
    -0.07
    ipp
    -0.07
     foes
    -0.07
    POSITIVE LOGITS
    ısı
    0.07
    oldur
    0.06
    شركة
    0.06
    зация
    0.06
     концентра
    0.06
     varying
    0.06
     iş
    0.06
    čních
    0.06
    ünün
    0.06
    variation
    0.06
    Act Density 0.105%

    No Known Activations