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

    Neuronpedia

    INDEX
    Explanations

    can't believe it's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mathfrak
    1.31
    __()
    1.29
     andando
    1.27
     جارہ
    1.26
    śmy
    1.26
    empat
    1.24
    ፍተኛ
    1.24
     drept
    1.24
    บคุม
    1.23
    (\
    1.23
    POSITIVE LOGITS
    त
    1.74
    ँ
    1.50
     regard
    1.49
    ﺭ
    1.41
    lN
    1.32
    dokument
    1.32
    ו
    1.32
    ႈ
    1.30
    з
    1.29
     setIsLoading
    1.29
    Act Density 0.002%

    No Known Activations