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

    Neuronpedia

    INDEX
    Explanations

    LaTeX formatting and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਹੀ
    0.40
    GLASS
    0.38
     DIA
    0.38
    硯
    0.38
     CRYST
    0.37
     Peppers
    0.37
     রান
    0.37
    ર્ચ
    0.36
    dze
    0.36
    Emojis
    0.36
    POSITIVE LOGITS
    renewcommand
    0.51
    @
    0.49
     redefined
    0.48
    citenamefont
    0.47
    \@
    0.45
     aux
    0.44
    ift
    0.42
     chapter
    0.42
    iftung
    0.41
     Gegenwart
    0.41
    Act Density 0.002%

    No Known Activations