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

    Neuronpedia

    INDEX
    Explanations

    specifies details or additions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    噰
    0.47
     использование
    0.42
    0.42
    ಯೋಗ
    0.41
    類的
    0.41
    䫒
    0.41
     नमस्ते
    0.41
     занятия
    0.41
    Lycodon
    0.41
     গিয়েছিলেন
    0.41
    POSITIVE LOGITS
     yeniden
    0.42
    ylle
    0.42
    )$.
    0.42
    ela
    0.41
     empowered
    0.41
    k
    0.40
    ura
    0.40
     opnieuw
    0.39
    }))
    0.39
     disturbing
    0.39
    Act Density 0.001%

    No Known Activations