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

    Neuronpedia

    INDEX
    Explanations

    combinations and matrices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    minster
    0.71
    {
    0.67
    theorem
    0.64
     be
    0.63
    संख्यक
    0.63
     cím
    0.62
    க்க
    0.61
    ਤੇ
    0.60
    district
    0.60
    2
    0.60
    POSITIVE LOGITS
     creeps
    0.67
     lags
    0.66
     زده
    0.65
     erred
    0.64
    वेल
    0.63
     wares
    0.62
     lasts
    0.60
     endeavors
    0.60
     bilden
    0.59
     erhe
    0.59
    Act Density 0.001%

    No Known Activations