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

    Neuronpedia

    INDEX
    Explanations

    the presence of vertical bars and related formatting in a document

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

    `|` delimiter in tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Persson
    -0.37
    PÁG
    -0.37
     icônes
    -0.36
    paisaje
    -0.34
    ion
    -0.33
     Grafen
    -0.31
    Betyg
    -0.31
     Itali
    -0.31
     became
    -0.30
     bocetos
    -0.30
    POSITIVE LOGITS
     للاسماء
    0.84
    findpost
    0.79
     CanadaChoose
    0.75
    󠁢
    0.65
    GEBURTS
    0.65
    windowFixed
    0.65
     Waray
    0.64
    ########.
    0.63
    :+:
    0.63
     kasarigan
    0.63
    Act Density 0.003%

    No Known Activations