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

    Neuronpedia

    INDEX
    Explanations

    programming elements and structures related to data handling and manipulation

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

    Characters often found in code or markup

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions with brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $}}
    -0.65
    ',(
    -0.61
    ",{
    -0.57
    extAlignment
    -0.56
    Bioaccumulative
    -0.55
    </tfoot>
    -0.55
    )');
    -0.55
    _;
    -0.53
    ">'+
    -0.53
    ')}}
    -0.53
    POSITIVE LOGITS
    [
    1.25
    [\
    0.89
     [
    0.83
    [$
    0.80
    [.
    0.74
    [_
    0.73
    [(
    0.68
    [{
    0.67
    ['
    0.66
    [-
    0.64
    Act Density 0.686%

    No Known Activations