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

    Neuronpedia

    INDEX
    Explanations

    Integral, Era, anus, Castle, story, Script

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ق
    0.48
     Sandro
    0.46
    ب
    0.46
    드
    0.45
    StarGo
    0.45
     camin
    0.44
    현재
    0.44
    த
    0.44
    StarObject
    0.43
     Meghna
    0.43
    POSITIVE LOGITS
    rijf
    0.47
     comparative
    0.45
     Comparative
    0.44
    ium
    0.41
    json
    0.41
    strip
    0.40
    gren
    0.40
    asin
    0.40
    module
    0.40
    station
    0.39
    Act Density 0.003%

    No Known Activations