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

    Neuronpedia

    INDEX
    Explanations

    occurrences of curly braces in code snippets

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

    code snippets and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ModelAndView
    -0.39
    ्
    -0.36
     inalámbrico
    -0.34
    nib
    -0.34
     mukana
    -0.34
     Constitucional
    -0.33
     ofici
    -0.33
     marquées
    -0.32
    ICES
    -0.32
    BUFF
    -0.32
    POSITIVE LOGITS
    ValueStyle
    0.65
    parsedMessage
    0.60
    RectangleBorder
    0.59
    encodeWith
    0.59
    aarrggbb
    0.57
     Italijani
    0.55
    httphttps
    0.54
     Мексичка
    0.53
    Géographie
    0.53
    CompleteListener
    0.52
    Act Density 0.003%

    No Known Activations