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

    Neuronpedia

    INDEX
    Explanations

    endings and conclusions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TreeWidgetItem
    0.42
     মাঝে
    0.42
    ἅ
    0.41
    ಿಸಲಾಗಿದೆ
    0.39
     آدم
    0.39
    امن
    0.39
    '}}
    0.39
    ْ
    0.38
     अधिका
    0.38
    以下の
    0.38
    POSITIVE LOGITS
     end
    0.98
     концов
    0.97
     End
    0.84
    end
    0.81
    ToEnd
    0.77
     END
    0.75
    端
    0.73
    End
    0.73
     ends
    0.66
    gült
    0.65
    Act Density 0.034%

    No Known Activations