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

    Neuronpedia

    INDEX
    Explanations

    your documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Myst
    0.88
    ред
    0.85
    Эк
    0.85
    Ку
    0.84
    Кроме
    0.82
    Gün
    0.80
    Nä
    0.79
    Kons
    0.77
    Де
    0.77
    prüfung
    0.77
    POSITIVE LOGITS
     Testosterone
    0.77
     airbags
    0.77
     tires
    0.73
     rgba
    0.73
     namespaces
    0.73
     მაშინ
    0.73
     islands
    0.71
     vibes
    0.71
     lemma
    0.70
     eigenstates
    0.70
    Act Density 2.437%

    No Known Activations