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

    Neuronpedia

    INDEX
    Explanations

    repeated occurrences of the word "the."

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

    article followed by capitalized entity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.69
     تضيفلها
    -0.65
    ChildScrollView
    -0.63
    windowFixed
    -0.62
     nakalista
    -0.62
    verwijspagina
    -0.59
     ujednoznacz
    -0.59
    turkish
    -0.58
    MergeFrom
    -0.57
    gonic
    -0.57
    POSITIVE LOGITS
     penting
    0.53
     pihaknya
    0.52
     peringatan
    0.50
     määrä
    0.48
     avulla
    0.48
     seharusnya
    0.46
     tarko
    0.46
     dėl
    0.45
     laikā
    0.45
     regalías
    0.44
    Act Density 0.015%

    No Known Activations