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

    Neuronpedia

    INDEX
    Explanations

    numerical data or identifiers

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

    Numbers

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions with numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XmlAccessorType
    -1.07
    Portale
    -0.95
    بوابة
    -0.95
    ViewFeatures
    -0.94
     ModelExpression
    -0.94
    Personensuche
    -0.93
     nahilalakip
    -0.89
     kasarigan
    -0.87
    GEBURTSDATUM
    -0.87
     désolés
    -0.84
    POSITIVE LOGITS
    4
    0.92
    2
    0.91
    6
    0.86
    9
    0.86
    1
    0.86
    7
    0.86
    8
    0.85
    3
    0.82
    5
    0.80
    0
    0.76
    Act Density 0.270%

    No Known Activations