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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and syntactical characters in code

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

    syntax delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.69
    dafx
    -0.55
     ویکی‌پدی
    -0.54
     Roskov
    -0.53
     EconPapers
    -0.51
     satisfecho
    -0.51
     herido
    -0.50
     afectado
    -0.49
    detectChanges
    -0.48
     almendras
    -0.47
    POSITIVE LOGITS
    @[+][
    0.45
    putString
    0.45
    prototype
    0.41
     monk
    0.41
     string
    0.41
    FloatField
    0.40
     bahia
    0.39
    ь
    0.39
     entero
    0.39
     long
    0.39
    Act Density 0.037%

    No Known Activations