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

    Neuronpedia

    INDEX
    Explanations

    what is next

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     goth
    0.43
     print
    0.41
     vertically
    0.39
     ave
    0.38
     ale
    0.37
    bi
    0.36
     disappointing
    0.36
    arence
    0.36
     defy
    0.36
     metrics
    0.35
    POSITIVE LOGITS
    まり
    0.43
     சேர்க்க
    0.43
    ശാസ്ത്ര
    0.41
    耇
    0.40
    スキン
    0.40
     रियर
    0.39
     ключе
    0.39
    تا
    0.38
     может
    0.38
     roupa
    0.38
    Act Density 0.000%

    No Known Activations