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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical operations and expressions, particularly those involving terms in equations

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

    "Collect the terms in"

    np_acts-logits-general · gemini-2.0-flash

    collect the terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.60
     فريبيس
    -0.56
    surate
    -0.55
     Waray
    -0.52
     Wikime
    -0.49
    OfDay
    -0.49
    nologies
    -0.49
    esterday
    -0.49
    >{@
    -0.48
    Demikian
    -0.47
    POSITIVE LOGITS
    AndEndTag
    0.88
    irst
    0.63
     AssemblyCulture
    0.62
     utilisons
    0.61
     vertes
    0.61
    consulté
    0.61
     aveug
    0.61
    Alright
    0.59
    ioutil
    0.59
     Educação
    0.59
    Act Density 0.595%

    No Known Activations