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

    Neuronpedia

    INDEX
    Explanations

    references to copyright issues and restrictions on the use of content

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

    Prohibiting actions, often copyright-related

    np_acts-logits-general · gemini-2.0-flash

    without permission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    correction
    -0.39
    canestro
    -0.38
     Corrections
    -0.35
    defer
    -0.35
    iseau
    -0.35
     conden
    -0.34
    darah
    -0.33
     Serializable
    -0.33
     Giud
    -0.33
    ViewHolder
    -0.33
    POSITIVE LOGITS
     without
    1.34
    without
    1.16
     unauthorized
    1.14
    Without
    1.13
     Without
    1.10
     unauthorised
    1.09
     tanpa
    1.06
     zonder
    1.06
     ohne
    1.02
    勝手に
    1.02
    Act Density 0.513%

    No Known Activations