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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    LaTeX math symbols

    np_acts-logits-general · gemini-2.0-flash

    Greek letters and math symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    もしれません
    -0.62
    ي
    -0.61
     Schult
    -0.61
    jména
    -0.60
    IBOutlet
    -0.60
    BeginInit
    -0.57
     Langen
    -0.56
     Сер
    -0.56
    orten
    -0.55
    なく
    -0.54
    POSITIVE LOGITS
     AssemblyCulture
    0.99
    
    0.93
    tableFuture
    0.89
     disambiguazione
    0.86
    %\
    0.85
    riwal
    0.84
    ']))
    0.83
    ()\
    0.83
    ftagPool
    0.82
    "])
    0.80
    Act Density 0.506%

    No Known Activations