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

    Neuronpedia

    INDEX
    Explanations

    bracketed references or citations in academic texts

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

    see section

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.68
    Tembelea
    -0.63
     Administrativna
    -0.61
    XmlAccessorType
    -0.53
    RTSC
    -0.52
    CopyWith
    -0.51
    aarrggbb
    -0.51
     '\\;'
    -0.51
    XmlEnum
    -0.50
     jsPsych
    -0.47
    POSITIVE LOGITS
     [
    0.62
    .[
    0.52
    )[
    0.50
    /[
    0.48
     ["
    0.48
    }[
    0.48
    [
    0.47
    ][
    0.47
     ['
    0.46
    <sup>
    0.46
    Act Density 0.097%

    No Known Activations