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

    Neuronpedia

    INDEX
    Explanations

    expressions related to evaluation and judgment of written content

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

    job, coaching, facts, mobile, supplied, advisable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informée
    -0.50
    sizeCache
    -0.48
    niająca
    -0.46
    sihkan
    -0.45
    SourceChecksum
    -0.44
    AddTagHelper
    -0.42
    GIVEREF
    -0.41
    classifiers
    -0.41
    figsize
    -0.41
     yyr
    -0.40
    POSITIVE LOGITS
     pouvoit
    0.56
     mourut
    0.47
     transferência
    0.46
     étoit
    0.45
     auroit
    0.45
     goederen
    0.44
     tłuma
    0.44
     abstrato
    0.43
     Serikat
    0.42
    '])->
    0.42
    Act Density 0.822%

    No Known Activations