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

    Neuronpedia

    INDEX
    Explanations

    significant proper nouns or notable names in context

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

    separating quotes from sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     klat
    -0.32
     multip
    -0.32
     dark
    -0.31
     subject
    -0.31
     autorytatywna
    -0.30
     Lightboxes
    -0.30
     trace
    -0.30
     bast
    -0.30
    yfikacja
    -0.30
    xodo
    -0.30
    POSITIVE LOGITS
    fromnode
    0.66
    OGND
    0.57
     insuffisamment
    0.56
    MigrationBuilder
    0.54
    Rüyada
    0.52
     مشين
    0.52
    SBATCH
    0.52
    transQ
    0.52
    ChrTalk
    0.51
    Hochspringen
    0.50
    Act Density 0.423%

    No Known Activations