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

    Neuronpedia

    INDEX
    Explanations

    references to geometric or graphical shapes

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

    "shape"

    np_acts-logits-general · gemini-2.0-flash

    shape description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.50
    __(/*!
    -0.47
    }{*}{
    -0.43
     nonexistent
    -0.42
     fewest
    -0.40
     összes
    -0.39
     Niet
    -0.38
     üçün
    -0.38
    Билгалдахарш
    -0.35
     Cummins
    -0.35
    POSITIVE LOGITS
    shape
    2.33
     shape
    2.28
     Shape
    2.27
    Shape
    2.23
    SHAPE
    2.06
     SHAPE
    2.06
    hape
    1.80
     shapes
    1.80
    shapes
    1.75
     Shapes
    1.73
    Act Density 0.070%

    No Known Activations