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

    Neuronpedia

    INDEX
    Explanations

    whitespace or spacing patterns in the data

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

    code keywords and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.65
    ⓧ
    -0.48
    setVerticalGroup
    -0.48
     Савезне
    -0.47
     linkovi
    -0.47
    ThroughAttribute
    -0.47
    SuspendLayout
    -0.46
    蚪
    -0.44
    SerializedSize
    -0.44
     Previously
    -0.43
    POSITIVE LOGITS
     تضيفلها
    0.52
     الاطلاع
    0.46
     kasarigan
    0.44
     bienven
    0.42
     decât
    0.41
     inmun
    0.40
     clín
    0.39
     invece
    0.39
    MENAFN
    0.39
     Administrativna
    0.39
    Act Density 0.005%

    No Known Activations