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

    Neuronpedia

    INDEX
    Explanations

    variable declarations and expectations in code

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

    variable declarations with types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fehl
    -0.33
    łas
    -0.33
    tmp
    -0.30
     aufzu
    -0.30
     pikir
    -0.28
    AutoField
    -0.28
     Consequently
    -0.28
    giphy
    -0.28
    auto
    -0.28
     tmp
    -0.28
    POSITIVE LOGITS
     EconPapers
    0.61
    WireFormatLite
    0.59
    AddTagHelper
    0.59
    iſen
    0.56
     ſol
    0.56
     ſtate
    0.55
    Démographie
    0.51
    TagHelper
    0.51
    WebElementEntity
    0.51
     obſ
    0.50
    Act Density 0.000%

    No Known Activations