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

    Neuronpedia

    INDEX
    Explanations

    intentionally or unlawfully

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Süden
    0.77
     хочется
    0.75
     copyspace
    0.74
     Всё
    0.74
     ऐप्स
    0.73
     プレゼント
    0.73
     myCamera
    0.72
     защото
    0.70
    вання
    0.70
     още
    0.70
    POSITIVE LOGITS
     pursuant
    0.87
    하거나
    0.87
     veya
    0.86
     prohibited
    0.84
     unlawfully
    0.84
     or
    0.82
     hoặc
    0.82
     materially
    0.81
     negligently
    0.81
     persons
    0.79
    Act Density 0.069%

    No Known Activations