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

    Neuronpedia

    INDEX
    Explanations

    dignity and, given, scraping sound, officially called

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     approximate
    0.46
    approx
    0.45
    provide
    0.45
    ประมาณ
    0.41
    often
    0.41
    agi
    0.39
    準
    0.39
    giant
    0.38
    を提供する
    0.37
     Approximate
    0.37
    POSITIVE LOGITS
    MSFontService
    0.45
     здійс
    0.44
    vođa
    0.43
     LMB
    0.42
     invece
    0.41
     població
    0.41
    ატ
    0.41
    тельству
    0.41
     sejahtera
    0.40
     музи
    0.40
    Act Density 0.000%

    No Known Activations