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

    Neuronpedia

    INDEX
    Explanations

    political titles and references to leadership roles

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

    political leaders titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الرياضيه
    -0.60
     հղումներ
    -0.59
    expandindo
    -0.57
    Hauptartikel
    -0.56
    AddTagHelper
    -0.56
    __(/*!
    -0.53
    setVerticalGroup
    -0.53
    下载附件
    -0.50
     autorytatywna
    -0.50
     NSCoder
    -0.50
    POSITIVE LOGITS
     Trump
    0.40
     Obrador
    0.39
    mergeFrom
    0.38
    spartner
    0.37
    patine
    0.34
     Constitu
    0.32
     Chamberlain
    0.32
    Trump
    0.31
    uterte
    0.31
     benzin
    0.31
    Act Density 0.039%

    No Known Activations