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

    Neuronpedia

    INDEX
    Explanations

    programmed to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    吅
    0.44
     обеспечи
    0.44
    щик
    0.42
     assisting
    0.41
     matching
    0.41
    ຖືກ
    0.40
     providing
    0.40
    matching
    0.40
     pTM
    0.40
    baiki
    0.39
    POSITIVE LOGITS
     nowoczes
    0.43
     Многие
    0.43
     दुनिया
    0.42
     niezwy
    0.42
     September
    0.41
     romant
    0.40
     세상
    0.39
    以來
    0.39
     certamente
    0.38
     многи
    0.38
    Act Density 0.042%

    No Known Activations