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

    Neuronpedia

    INDEX
    Explanations

    dark background

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     чого
    0.46
    כו
    0.45
    天堂
    0.43
    ๚
    0.42
     kost
    0.41
    וד
    0.40
    odox
    0.40
     מה
    0.40
     fejl
    0.40
     behö
    0.40
    POSITIVE LOGITS
     {
    0.45
    school
    0.43
     શિક્ષણ
    0.42
    label
    0.41
     कार्यक्रम
    0.41
    ပြ
    0.41
    context
    0.40
     သ
    0.40
     cuyas
    0.39
     syllabus
    0.39
    Act Density 0.004%

    No Known Activations