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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and structure in code

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

    rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.66
     صوتيه
    -0.62
    bootstrapcdn
    -0.61
    JspWriter
    -0.61
     незавершена
    -0.60
    -0.56
    ValueStyle
    -0.56
    RTEX
    -0.55
     nahilalakip
    -0.55
    OGND
    -0.54
    POSITIVE LOGITS
     rules
    1.00
    rules
    0.83
    Rules
    0.81
     Rules
    0.77
     RULES
    0.75
     regulations
    0.71
     règles
    0.70
     Regeln
    0.70
     reglas
    0.68
    规则
    0.66
    Act Density 0.002%

    No Known Activations