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

    Neuronpedia

    INDEX
    Explanations

    descriptions and variations of shapes and structures

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

    physical shape description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <>",
    -0.74
     المعيارى
    -0.71
     $_"
    -0.71
    UnitTesting
    -0.70
     indígen
    -0.63
    addContainerGap
    -0.63
    ſelben
    -0.63
    <unused41>
    -0.61
    <unused23>
    -0.61
    <unused8>
    -0.61
    POSITIVE LOGITS
     shape
    1.14
     shapes
    0.98
     shaped
    0.93
     Shape
    0.91
    Shape
    0.87
    SHAPE
    0.86
    shape
    0.85
    shapes
    0.83
    shaped
    0.82
     SHAPE
    0.81
    Act Density 0.030%

    No Known Activations