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

    Neuronpedia

    INDEX
    Explanations

    fulfillment process

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    неоп
    0.48
     nível
    0.46
     தினம்
    0.46
    硞
    0.46
     fakult
    0.45
    phans
    0.44
    聁
    0.44
    нами
    0.43
    妏
    0.43
    ುವುದಿಲ್ಲ
    0.42
    POSITIVE LOGITS
     여러
    0.54
     가면
    0.48
    arding
    0.45
     የተለያዩ
    0.45
     कब
    0.43
     marit
    0.42
     предпо
    0.42
     dormant
    0.42
     dov
    0.41
     밝
    0.41
    Act Density 0.002%

    No Known Activations