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

    Neuronpedia

    INDEX
    Explanations

    Health and common issues

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Entrenamiento
    0.60
     여러분
    0.59
     Wider
    0.55
    ときの
    0.55
    udu
    0.54
     ضع
    0.54
    dumps
    0.54
    ặ
    0.54
     Zaman
    0.53
     Watan
    0.52
    POSITIVE LOGITS
     gardening
    0.61
     hillside
    0.56
    蕌
    0.56
     seafood
    0.55
    мите
    0.54
     nets
    0.54
     thatch
    0.54
     netted
    0.53
    钓
    0.53
     sprung
    0.52
    Act Density 0.000%

    No Known Activations