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

    Neuronpedia

    INDEX
    Explanations

    some numbers, particularly percentages, and also the word "agree"

    oai_token-act-pair · gemini-2.0-flash

    programming-related tokens

    np_token-act-pair-logits · gpt-4o-mini

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ogada
    -0.62
    IMPORTED
    -0.57
    ficulty
    -0.56
    UnusedPrivate
    -0.54
    jsdelivr
    -0.54
    probability
    -0.52
     irmã
    -0.51
     grü
    -0.50
    Fordítás
    -0.50
    Erreferentziak
    -0.50
    POSITIVE LOGITS
    ̍t
    0.58
    setVerticalGroup
    0.56
    +#+#
    0.54
     resultCode
    0.53
    tvguidetime
    0.52
    HtmlAttribute
    0.50
    kháu
    0.48
     pleaſure
    0.48
    :✨
    0.47
    styleType
    0.47
    Act Density 1.633%

    No Known Activations