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

    Neuronpedia

    INDEX
    Explanations

    instances of the start of a document or textual input

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

    numbers and names preceding citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тьяна
    -0.67
     Geraadpleegd
    -0.63
    таратура
    -0.59
     noqa
    -0.57
    Источник
    -0.56
     télévis
    -0.55
    ğraf
    -0.55
     Wissenschaften
    -0.55
     CanadaChoose
    -0.54
     bestand
    -0.54
    POSITIVE LOGITS
    0
    0.80
    AddTagHelper
    0.75
    1
    0.71
    2
    0.68
     Naw
    0.67
    5
    0.63
    3
    0.62
    󠁢
    0.62
     Nau
    0.61
     HasFactory
    0.60
    Act Density 0.239%

    No Known Activations