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

    Neuronpedia

    INDEX
    Explanations

    fictional story examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    剤
    0.46
    ץ
    0.44
    نا
    0.43
    ையா
    0.43
    üğünüz
    0.43
    我
    0.43
    ש
    0.43
    제
    0.43
    ду
    0.42
    вого
    0.42
    POSITIVE LOGITS
     ór
    0.48
    देख
    0.48
     instru
    0.43
     sewing
    0.42
     argumento
    0.42
     hoff
    0.42
     przes
    0.41
     sikap
    0.41
     új
    0.40
     Padukone
    0.40
    Act Density 0.006%

    No Known Activations