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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and formatting elements

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

    special characters and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.77
    :✨
    -0.74
    KommentareTeilen
    -0.69
    AISSEE
    -0.68
     незавершена
    -0.65
     kaarangay
    -0.64
     autorytatywna
    -0.64
     ostavi
    -0.63
    BeginContext
    -0.61
    -0.60
    POSITIVE LOGITS
     chercheurs
    0.34
    multline
    0.28
     bénévoles
    0.27
    EndTag
    0.26
    forRoot
    0.26
     inalámb
    0.26
    แผ
    0.26
     Komponist
    0.26
     çocu
    0.26
     tránsito
    0.26
    Act Density 0.158%

    No Known Activations