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

    Neuronpedia

    INDEX
    Explanations

    discussions and descriptions of shapes

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

    "shape" or "shapes"

    np_acts-logits-general · gemini-2.0-flash

    shape of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RUnlock
    -0.80
    Referencie
    -0.78
    NewLabel
    -0.78
    例句
    -0.78
    esModule
    -0.77
     MenuView
    -0.77
    ChildIndex
    -0.76
     Deuter
    -0.75
    CodedInputStream
    -0.75
    wój
    -0.74
    POSITIVE LOGITS
     SHAPE
    1.71
     shape
    1.69
     shapes
    1.68
     Shape
    1.59
     Shapes
    1.55
    shapes
    1.53
    SHAPE
    1.52
    shape
    1.47
    Shape
    1.41
    Shapes
    1.36
    Act Density 0.093%

    No Known Activations