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

    Neuronpedia

    INDEX
    Explanations

    blocks of whitespace or specific formatting characters

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

    Code or special characters

    np_acts-logits-general · gemini-2.0-flash

    code comments and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -1.13
     CreateTagHelper
    -0.85
     resourceCulture
    -0.80
    utives
    -0.80
    SBATCH
    -0.78
    醐
    -0.78
    Билгалдахарш
    -0.76
    endphp
    -0.76
    TypedDataSet
    -0.74
    tagext
    -0.73
    POSITIVE LOGITS
    nie
    0.57
    <b>
    0.51
    EndGlobalSection
    0.49
     upor
    0.48
    a
    0.48
    ols
    0.47
    //
    0.47
     glycer
    0.47
    ل
    0.47
     Lizzy
    0.46
    Act Density 0.373%

    No Known Activations