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

    Neuronpedia

    INDEX
    Explanations

    action verbs indicating transition or progress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informace
    0.30
     jakieś
    0.29
     nějak
    0.28
     മനസ
    0.28
     ಒಳ್ಳೆಯ
    0.27
    อะไร
    0.27
     prépuce
    0.27
    ）・
    0.27
     informacje
    0.27
     люди
    0.26
    POSITIVE LOGITS
     penchant
    0.28
     belated
    0.27
     darling
    0.27
     reshaping
    0.26
     erstwhile
    0.26
     scathing
    0.26
     celebrated
    0.26
     본격
    0.26
     grueling
    0.25
     the
    0.25
    Act Density 0.056%

    No Known Activations