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

    Neuronpedia

    INDEX
    Explanations

    references to personal relationships and familial connections

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

    possessive pronouns and family names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pind
    -0.47
    Hentet
    -0.46
    filtr
    -0.43
     mui
    -0.42
    redients
    -0.41
    zep
    -0.40
    qiu
    -0.40
     eint
    -0.40
    toprule
    -0.40
     հղումներ
    -0.40
    POSITIVE LOGITS
    niająca
    0.48
     defaultstate
    0.48
    تقاوى
    0.47
    󠁴
    0.43
    ultados
    0.42
    ThroughAttribute
    0.42
     coroa
    0.42
    contentLoaded
    0.42
     vī
    0.41
    actionMode
    0.41
    Act Density 0.002%

    No Known Activations