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

    Neuronpedia

    INDEX
    Explanations

    references to gaps or openings in structures or systems

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

    holes and gaps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HERBERT
    -0.32
    zelfde
    -0.31
    Daphne
    -0.31
     contemporaine
    -0.30
     bou
    -0.30
    thâu
    -0.30
     devriez
    -0.29
    farwydd
    -0.28
     kyl
    -0.27
     hex
    -0.27
    POSITIVE LOGITS
     Holes
    0.64
     holes
    0.61
    IsMutable
    0.60
     gaps
    0.60
    Holes
    0.59
    Билгалдахарш
    0.59
     Hole
    0.58
    RectangleBorder
    0.57
     Gaps
    0.57
     hole
    0.57
    Act Density 0.193%

    No Known Activations