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

    Neuronpedia

    INDEX
    Explanations

    how to do something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     meestal
    0.38
     약간
    0.37
     Rahe
    0.37
     பெரும்பாலும்
    0.35
     bis
    0.35
     kuten
    0.34
     чаще
    0.34
     normalement
    0.34
     일반적으로
    0.34
     coche
    0.33
    POSITIVE LOGITS
     如何
    0.52
    如何
    0.49
     sufficiently
    0.49
     كيفية
    0.46
     എങ്ങനെ
    0.45
    如何在
    0.45
     satisfactorily
    0.41
    どのように
    0.40
     কিভাবে
    0.39
     seamlessly
    0.38
    Act Density 0.148%

    No Known Activations