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

    Neuronpedia

    INDEX
    Explanations

    university names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ერ
    0.65
    िख
    0.64
    Vol
    0.62
    να
    0.59
     autoradi
    0.58
    ల
    0.58
    λι
    0.57
    PrintError
    0.57
    లు
    0.56
    ော်
    0.56
    POSITIVE LOGITS
     Jesuit
    0.84
     Loyola
    0.82
     Franciscan
    0.70
    edges
    0.70
     Fordham
    0.70
    edere
    0.66
    ediaan
    0.64
     FanDuel
    0.64
     years
    0.64
    esque
    0.64
    Act Density 0.001%

    No Known Activations