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

    Neuronpedia

    INDEX
    Explanations

    qualities or characteristics relevant to research findings and outcomes

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

    including or disambiguation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cyfarwyddwr
    -0.52
    Билгалдахарш
    -0.44
    Jeografia
    -0.44
    GEBURTSDATUM
    -0.43
    roffen
    -0.40
    渡
    -0.39
    atguigu
    -0.38
     throm
    -0.37
     кӀош
    -0.37
     malignant
    -0.37
    POSITIVE LOGITS
     disambiguazione
    0.69
     including
    0.59
     včetně
    0.58
     ujednoznacz
    0.56
    पया
    0.54
    including
    0.52
     Including
    0.51
    Including
    0.50
    RuleContext
    0.48
    包括
    0.47
    Act Density 0.074%

    No Known Activations