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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax and structure in programming languages

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

    Code snippets involving parentheses or brackets

    np_acts-logits-general · gemini-2.0-flash

    function and class definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ihm
    -0.52
     mög
    -0.49
     skimming
    -0.48
    略
    -0.47
     allerede
    -0.47
    parseLong
    -0.46
    ='".$
    -0.46
     effectually
    -0.45
    ächter
    -0.45
    σμα
    -0.44
    POSITIVE LOGITS
    DockStyle
    0.87
    GEBURTSDATUM
    0.67
    LookAnd
    0.65
     hello
    0.63
    +#+#
    0.60
    foo
    0.58
     Foo
    0.57
    HasAnnotation
    0.56
    帖最后由
    0.56
    hello
    0.56
    Act Density 0.581%

    No Known Activations