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

    Neuronpedia

    INDEX
    Explanations

    actions and results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ବ
    0.49
     प्रसि
    0.47
    evenly
    0.44
     Resultados
    0.42
    ıldı
    0.41
     कामया
    0.41
    abajo
    0.41
    beitet
    0.40
    サッカー
    0.40
    angé
    0.40
    POSITIVE LOGITS
    FindFirst
    0.47
     crucial
    0.43
     получить
    0.39
    行為
    0.38
    获取
    0.36
     minimum
    0.36
    ↵↵↵
    0.35
     deal
    0.35
    を獲得
    0.35
     procuring
    0.35
    Act Density 0.001%

    No Known Activations