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

    Neuronpedia

    INDEX
    Explanations

    references to specific points or locations within a context

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

    point of view

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    utzung
    -0.35
    arrol
    -0.34
     Harwood
    -0.34
    Utilisation
    -0.33
     sanitarias
    -0.33
    six
    -0.33
     Schä
    -0.33
    abled
    -0.33
    uesta
    -0.32
     Navarra
    -0.32
    POSITIVE LOGITS
     point
    1.41
     points
    1.35
    point
    1.32
     punto
    1.27
    points
    1.27
    POINT
    1.25
     Point
    1.25
    Point
    1.24
     Points
    1.24
    punto
    1.23
    Act Density 0.018%

    No Known Activations