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

    Neuronpedia

    INDEX
    Explanations

    Philosophy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Рос
    -0.06
     bekommen
    -0.06
     özgür
    -0.06
     pů
    -0.06
     огра
    -0.06
    Чтобы
    -0.06
     допомоги
    -0.06
     onPressed
    -0.06
     mapView
    -0.06
     افزار
    -0.06
    POSITIVE LOGITS
    esch
    0.07
     leaves
    0.07
    ennen
    0.06
     Conversely
    0.06
    such
    0.06
    ercul
    0.06
    VB
    0.06
    .bc
    0.06
     Jens
    0.06
     instruct
    0.06
    Act Density 0.042%

    No Known Activations