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

    Neuronpedia

    INDEX
    Explanations

    calculates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     leveraged
    0.70
    новить
    0.67
    柟
    0.63
    یز
    0.63
    rb
    0.62
    含ま
    0.62
    orea
    0.62
     sikre
    0.61
    ﯽ
    0.61
     समझना
    0.61
    POSITIVE LOGITS
     excitedly
    0.72
    ಾಗಲೇ
    0.71
     xinh
    0.68
     、,
    0.66
     ragazza
    0.66
    ously
    0.65
     République
    0.65
     Ecusson
    0.63
    まず
    0.63
     śmierci
    0.62
    Act Density 0.001%

    No Known Activations