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

    Neuronpedia

    INDEX
    Explanations

    code structures and data manipulations within programming contexts

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

    Code or expressions using symbols like =, !=, or ()

    np_acts-logits-general · gemini-2.0-flash

    code blocks with assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DIPSETTING
    -0.85
     queſta
    -0.82
     BoxFit
    -0.82
    aarrggbb
    -0.81
    GTCX
    -0.76
    GEBURTSDATUM
    -0.76
     للاسماء
    -0.71
     Administrativna
    -0.71
     defaultstate
    -0.70
     myſelf
    -0.69
    POSITIVE LOGITS
     пода
    0.36
     ayr
    0.35
    Espèce
    0.34
     Fürsten
    0.33
     directamente
    0.32
    attuale
    0.32
     Fürst
    0.32
     literally
    0.32
     individually
    0.31
     sağlay
    0.31
    Act Density 0.171%

    No Known Activations