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

    Neuronpedia

    INDEX
    Explanations

    non-activating tokens or separators in the document

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

    Code-related punctuation and symbols

    np_acts-logits-general · gemini-2.0-flash

    of granular materials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     clearColor
    -0.66
     pstmt
    -0.61
    neſs
    -0.59
     photolibrary
    -0.58
     FontWeight
    -0.58
     atof
    -0.56
     CommandType
    -0.56
     Balkan
    -0.55
    NoSuchAlgorithm
    -0.55
     gddr
    -0.54
    POSITIVE LOGITS
     "";
    0.89
    RegressionTest
    0.80
    ；
    0.78
    ;',
    0.77
    )))));
    0.76
    sizeCache
    0.76
    ']],
    0.75
    '));
    0.74
    >>;
    0.72
     {};
    0.72
    Act Density 0.078%

    No Known Activations