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

    Neuronpedia

    INDEX
    Explanations

    "?> closing tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     साधन
    0.42
     propre
    0.42
     cier
    0.41
     клю
    0.41
    招
    0.41
     wary
    0.39
     debugger
    0.39
    cien
    0.39
     chosen
    0.39
     선
    0.39
    POSITIVE LOGITS
     Pott
    0.46
    ⏫
    0.43
    itage
    0.42
    ᐈ
    0.41
    amız
    0.41
    성의
    0.41
     পাহাড়
    0.41
    英國
    0.40
    😲
    0.40
     sedangkan
    0.40
    Act Density 0.000%

    No Known Activations