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

    Neuronpedia

    INDEX
    Explanations

    structured data or code snippets related to functions or tables in documents

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

    Symbols indicating changes or types

    np_acts-logits-general · gemini-2.0-flash

    punctuation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ".
    -0.86
    .";
    -0.86
     كومونز
    -0.85
    .",
    -0.84
    !")
    -0.73
    '},
    -0.72
    Datuak
    -0.69
    "):
    -0.67
    ?
    -0.67
    %</
    -0.66
    POSITIVE LOGITS
    ꒳
    0.76
     ddelweddau
    0.69
    ethene
    0.68
     glucocortico
    0.66
     chlorophyll
    0.64
     monocytes
    0.62
     defStyleAttr
    0.60
     &&
    0.60
     witchcraft
    0.60
     Margot
    0.59
    Act Density 0.852%

    No Known Activations