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

    Neuronpedia

    INDEX
    Explanations

    occurrences of backslashes and related syntax in programming contexts

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

    technical file paths and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    scriptId
    -0.46
     ioutil
    -0.38
    endphp
    -0.38
     Victims
    -0.36
     drep
    -0.34
     creș
    -0.34
    jería
    -0.33
    wapV
    -0.33
    MLLoader
    -0.33
     învă
    -0.33
    POSITIVE LOGITS
    OGND
    0.56
     snippetHide
    0.52
    AddTagHelper
    0.52
    thâu
    0.46
    yntaxException
    0.46
    mband
    0.46
    RenderAtEndOf
    0.45
    Spoljašnje
    0.44
    acheco
    0.44
    DoubleQuotes
    0.43
    Act Density 0.466%

    No Known Activations