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

    Neuronpedia

    INDEX
    Explanations

    instances of programming-related variables and functions

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

    Code-related terms followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    variable assignments followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "");
    -0.82
    )++;
    -0.67
     """
    -0.62
     ''
    -0.61
     '').
    -0.60
    "]);
    -0.60
    _;
    -0.59
     "").
    -0.59
     ""));
    -0.58
    _))
    -0.58
    POSITIVE LOGITS
    migrationBuilder
    0.79
    henswürdigkeiten
    0.61
    ModelAttribute
    0.61
    RSpec
    0.54
    .
    0.53
    PositiveButton
    0.53
    +#+#
    0.52
    $_['
    0.51
    freiheit
    0.51
    isFetching
    0.51
    Act Density 0.424%

    No Known Activations