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

    Neuronpedia

    INDEX
    Explanations

    phrases related to error handling and function calls in code

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

    calls, invoked, methods, significant, vanish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.79
     myſelf
    -0.77
    ########.
    -0.77
     BoxFit
    -0.68
     كومونز
    -0.66
     الحره
    -0.65
    الحياه
    -0.63
    GraphicsUnit
    -0.62
     ſche
    -0.59
     strconv
    -0.54
    POSITIVE LOGITS
    toHaveBeenCalled
    2.36
    setAccessible
    0.55
    Called
    0.53
     occurred
    0.51
     occur
    0.45
    cedido
    0.45
    toHaveBeen
    0.44
     Called
    0.42
     Taken
    0.42
    Calls
    0.40
    Act Density 0.001%

    No Known Activations