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

    Neuronpedia

    INDEX
    Explanations

    references to the term "same" in various contexts

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

    referring to a previously mentioned thing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OSPH
    -0.31
     reigning
    -0.29
    rik
    -0.28
    ichts
    -0.28
    PORT
    -0.26
     SURV
    -0.26
     RESID
    -0.25
    itu
    -0.25
    ÁND
    -0.25
     Spokes
    -0.25
    POSITIVE LOGITS
    IsMutable
    0.81
    uxxxx
    0.78
    AndEndTag
    0.75
    Personensuche
    0.73
    Diwedd
    0.73
    NameInMap
    0.68
     مشين
    0.67
    Jeografia
    0.65
    twimg
    0.65
    SaveChangesAsync
    0.64
    Act Density 0.173%

    No Known Activations