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

    Neuronpedia

    INDEX
    Explanations

    and Daily

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⬮
    0.40
     désigne
    0.40
     avrà
    0.40
     intégré
    0.39
     lak
    0.39
    лії
    0.38
     fases
    0.38
     dentre
    0.38
     falo
    0.38
     legge
    0.37
    POSITIVE LOGITS
    ्यक्रम
    0.44
     Chem
    0.44
    匹配
    0.41
    Chem
    0.40
     Similar
    0.38
     sakta
    0.38
     CHEM
    0.38
    ಿಸಲಾಗಿದೆ
    0.38
     دقیق
    0.37
     matched
    0.37
    Act Density 0.000%

    No Known Activations