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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions pertaining to shapes and structures

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

    Geometric shapes or arrangements

    np_acts-logits-general · gemini-2.0-flash

    shape and form

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mark
    -0.50
     (
    -0.44
     I
    -0.44
     Sub
    -0.43
     W
    -0.42
     Mit
    -0.42
     my
    -0.42
     mark
    -0.41
    Mark
    -0.41
     By
    -0.41
    POSITIVE LOGITS
     shape
    0.82
    ########.
    0.81
     berbentuk
    0.78
    RectangleBorder
    0.77
     itſelf
    0.76
     CURIAM
    0.75
     sauvages
    0.73
    KommentareTeilen
    0.72
     виправивши
    0.71
     BorderRadius
    0.70
    Act Density 0.477%

    No Known Activations