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

    Neuronpedia

    INDEX
    Explanations

    blocks of code related to error handling in programming

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

    Code snippets or math expressions ending with specific punctuation

    np_acts-logits-general · gemini-2.0-flash

    ending state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.77
     PopupWindow
    -0.59
    hran
    -0.57
    ￡
    -0.56
    openqa
    -0.56
    apimachinery
    -0.55
    AddTagHelper
    -0.54
    jfree
    -0.54
    MemoryWarning
    -0.54
    Hauptartikel
    -0.54
    POSITIVE LOGITS
    finally
    0.79
     finally
    0.68
     FINALLY
    0.56
    FINALLY
    0.53
     Finally
    0.53
    ثيق
    0.51
    ########.
    0.50
     finalmente
    0.50
    autaire
    0.48
    Finally
    0.48
    Act Density 0.043%

    No Known Activations