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

    Neuronpedia

    INDEX
    Explanations

    probabilities and pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    besar
    0.43
    initis
    0.41
     Đại
    0.39
     જેમ
    0.38
     сооб
    0.38
    ownt
    0.37
     المغ
    0.37
    aptop
    0.36
     प्रतिद्व
    0.36
     Fu
    0.36
    POSITIVE LOGITS
    ätzlich
    0.42
     заключения
    0.38
     chad
    0.37
    Referències
    0.36
     autonom
    0.36
     shatter
    0.36
     submer
    0.36
    าท
    0.35
    chad
    0.35
     ಖರೀ
    0.35
    Act Density 0.060%

    No Known Activations