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

    Neuronpedia

    INDEX
    Explanations

    lists of words or terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    কাতে
    0.66
     $
    0.66
     tack
    0.65
     course
    0.64
    ones
    0.62
     terme
    0.62
     one
    0.61
     "$
    0.61
     Enterprise
    0.61
     ones
    0.60
    POSITIVE LOGITS
    activiti
    0.98
     выйти
    0.89
    что
    0.86
    Only
    0.82
    Só
    0.82
    颀
    0.81
    ዖ
    0.80
    ടി
    0.80
    jegyz
    0.80
    oscopy
    0.80
    Act Density 0.000%

    No Known Activations