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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical structures and alterations involving holes and cuts

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

    "in/through" followed by "the/a"

    np_acts-logits-general · gemini-2.0-flash

    holes in, through, into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.72
    ⓘ
    -0.68
     الرياضيه
    -0.63
    featureID
    -0.63
    AndEndTag
    -0.58
    IsMutable
    -0.57
     disambiguazione
    -0.56
    SharedDtor
    -0.56
    bollah
    -0.54
    ↺
    -0.54
    POSITIVE LOGITS
    Derbyniad
    0.57
     drywall
    0.54
    udur
    0.54
     texture
    0.51
     BorderRadius
    0.48
     recor
    0.46
    ulite
    0.46
     Texture
    0.46
     plane
    0.46
     textures
    0.46
    Act Density 0.584%

    No Known Activations