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

    Neuronpedia

    INDEX
    Explanations

    technology used, murders committed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     внед
    0.41
    承包人
    0.41
    ッズ
    0.40
    包人
    0.40
    ães
    0.38
    ifikation
    0.38
    科普
    0.38
     হইয়
    0.38
    іга
    0.38
    इल
    0.38
    POSITIVE LOGITS
     typing
    0.45
     Мин
    0.39
     itching
    0.38
    JAMES
    0.38
    ometry
    0.38
     bedrooms
    0.37
    bedrooms
    0.37
    Ω
    0.36
     ச
    0.35
    schw
    0.35
    Act Density 0.000%

    No Known Activations