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

    Neuronpedia

    INDEX
    Explanations

    references to authorship or attribution in text

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

    author tags in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lisäksi
    -0.38
    beitet
    -0.37
     yerine
    -0.35
     tarko
    -0.35
    WritableDatabase
    -0.35
     specifico
    -0.34
     yks
    -0.34
     gången
    -0.33
     Dougherty
    -0.33
    ɵɵ
    -0.33
    POSITIVE LOGITS
    rungsseite
    0.62
     surla
    0.61
    Author
    0.57
     Administrativna
    0.53
     Author
    0.52
     作者
    0.52
    AUTHOR
    0.52
     AUTHOR
    0.51
     мәкал
    0.51
    AtIndexPath
    0.50
    Act Density 0.000%

    No Known Activations