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

    Neuronpedia

    INDEX
    Explanations

    likely or guaranteed outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InMillis
    0.40
     greatest
    0.38
    irono
    0.38
    頂き
    0.37
     Carrasco
    0.37
     paramInt
    0.35
     especiais
    0.34
     programas
    0.33
     পড়েন
    0.33
     intervened
    0.33
    POSITIVE LOGITS
    aranteed
    0.49
     مكت
    0.46
     likely
    0.45
     Likely
    0.45
    likely
    0.45
     guaranteed
    0.44
    designed
    0.42
    ຖືກ
    0.41
    imt
    0.41
     delight
    0.41
    Act Density 0.009%

    No Known Activations