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

    Neuronpedia

    INDEX
    Explanations

    elements that indicate programming constructs and class definitions

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

    Code, APIs, and related programming elements

    np_acts-logits-general · gemini-2.0-flash

    code class definitions and methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.48
    Autoritní
    -0.44
    ConstraintMaker
    -0.40
    :✨
    -0.40
     yyb
    -0.39
    tagHelperRunner
    -0.36
    MigrationBuilder
    -0.36
    WithIOException
    -0.36
    httphttps
    -0.35
     Roskov
    -0.35
    POSITIVE LOGITS
    StructEnd
    0.52
     otomatig
    0.49
    delwed
    0.48
    orse
    0.47
     MacDonald
    0.46
    OPSIS
    0.44
    ueses
    0.43
    rachtet
    0.41
    delsen
    0.41
     optique
    0.41
    Act Density 0.221%

    No Known Activations