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

    Neuronpedia

    INDEX
    Explanations

    variables and constants typically used in programming languages

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

    programming variable declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    break
    -0.32
     Te
    -0.32
     almost
    -0.32
    AP
    -0.32
    almost
    -0.32
    onMouse
    -0.32
     therefrom
    -0.32
    Ap
    -0.31
    OfYear
    -0.31
     kap
    -0.31
    POSITIVE LOGITS
    $_['
    0.81
    OGND
    0.78
     snippetHide
    0.72
    parsedMessage
    0.71
    ########.
    0.70
     typelib
    0.68
     &___
    0.66
    ſicht
    0.66
    ésultats
    0.65
     $_"
    0.65
    Act Density 0.001%

    No Known Activations