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

    Neuronpedia

    INDEX
    Explanations

    punctuations and formatting symbols in a programming context

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

    tokens after delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.81
     <<<<<<<<<<<<<<
    -0.74
    \{\\
    -0.72
    ReusableCell
    -0.71
    RegressionTest
    -0.67
    LookAnd
    -0.66
    awtextra
    -0.66
    IUrlHelper
    -0.65
    expandindo
    -0.63
    parsedMessage
    -0.63
    POSITIVE LOGITS
     nuages
    0.42
    rechnung
    0.39
     Cloud
    0.37
     Spirit
    0.36
     also
    0.36
    Dona
    0.36
    setzen
    0.36
    Security
    0.36
     ilha
    0.36
     Peak
    0.36
    Act Density 0.002%

    No Known Activations