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

    Neuronpedia

    INDEX
    Explanations

    references to geometric shapes or shape-related terms

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

    shapes and shape operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Niet
    -0.56
     nonexistent
    -0.56
     thousand
    -0.49
     non
    -0.49
     fewest
    -0.48
    mdb
    -0.48
     Non
    -0.47
     onError
    -0.47
    NonNull
    -0.47
     unconditionally
    -0.47
    POSITIVE LOGITS
    Shape
    1.27
    SHAPE
    1.23
     Shape
    1.21
    shape
    1.18
     SHAPE
    1.13
     shape
    1.09
    hape
    1.01
    shapes
    0.88
     Shapes
    0.85
    Shapes
    0.83
    Act Density 0.010%

    No Known Activations