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

    Neuronpedia

    INDEX
    Explanations

    variable assignments and return statements in code snippets

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

    Code assignments using equals signs

    np_acts-logits-general · gemini-2.0-flash

    common programming identifiers and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )
    -0.56
    -0.52
     pstmt
    -0.50
    an
    -0.49
    ,
    -0.47
    ers
    -0.46
    ("")

    -0.42
    benzo
    -0.42
     bearing
    -0.41
    ’
    -0.40
    POSITIVE LOGITS
     CreateTagHelper
    1.20
     "";
    1.15
    [];
    1.14
    __;
    1.02
     [];
    1.00
    ;\\
    0.99
    '';
    0.97
     {};
    0.96
    ；
    0.96
    ?;
    0.96
    Act Density 0.207%
    No Known Activations