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

    Neuronpedia

    INDEX
    Explanations

    phrases related to claims, assertions, and their validity in the context of accountability and inquiry

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

    a claim or statement

    np_acts-logits-general · gemini-2.0-flash

    reporting claims or facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.86
    aarrggbb
    -0.65
    InputTagHelper
    -0.65
    AddTagHelper
    -0.61
    VersionUID
    -0.57
     BoxDecoration
    -0.57
    出版年
    -0.56
    extAlignment
    -0.56
    ագրություններ
    -0.56
    AndEndTag
    -0.56
    POSITIVE LOGITS
     picture
    0.42
     pic
    0.38
    Picture
    0.35
    picture
    0.35
     Италијани
    0.35
    け
    0.34
    allenge
    0.34
     pictures
    0.34
     small
    0.34
    atikan
    0.34
    Act Density 0.762%

    No Known Activations