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

    Neuronpedia

    INDEX
    Explanations

    indicators of code structure and control flow

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

    Code fragments/snippets

    np_acts-logits-general · gemini-2.0-flash

    html tags and plus sign

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.92
    SourceChecksum
    -0.90
    LLocation
    -0.85
     Efq
    -0.83
    IsMutable
    -0.82
     beginnetje
    -0.81
     photolibrary
    -0.80
     whoſe
    -0.78
    참고
    -0.78
     ſche
    -0.78
    POSITIVE LOGITS
    <unused61>
    0.65
    </i>
    0.63
    <unused60>
    0.63
    <unused62>
    0.60
    <unused63>
    0.58
    </b>
    0.52
    +
    0.50
     tal
    0.47
     luận
    0.47
     brazos
    0.45
    Act Density 0.167%

    No Known Activations