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

    Neuronpedia

    INDEX
    Explanations

    concepts and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    дово
    0.41
     паль
    0.39
    िकुलम
    0.38
     безо
    0.37
    saa
    0.37
    цеп
    0.37
     likewise
    0.37
     sqlType
    0.36
     Carlo
    0.36
    uldron
    0.36
    POSITIVE LOGITS
    freund
    0.51
    ون
    0.50
     दे
    0.50
     Tecn
    0.50
     الذي
    0.49
    德
    0.49
     ده
    0.48
    ם
    0.48
    를
    0.48
    ار
    0.47
    Act Density 0.003%

    No Known Activations