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

    Neuronpedia

    INDEX
    Explanations

    another followed by diverse subsequent terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ators
    0.64
     oth
    0.62
    ानों
    0.58
    ats
    0.58
    ities
    0.56
    alities
    0.54
    ิ
    0.54
    izers
    0.53
    ors
    0.52
    ות
    0.52
    POSITIVE LOGITS
    n
    0.57
     deň
    0.52
     περίπτωση
    0.50
     similaire
    0.49
     obie
    0.49
     embolism
    0.48
    വൻ
    0.48
     padlock
    0.47
    نظر
    0.47
     one
    0.47
    Act Density 0.009%

    No Known Activations