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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and assumptions in the text

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

    assuming positive variable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſta
    -0.59
     faſt
    -0.58
     viſ
    -0.52
     ſtand
    -0.52
    المناصب
    -0.52
     ſever
    -0.50
    expandindo
    -0.49
     ſur
    -0.49
     deſt
    -0.49
     paſſ
    -0.48
    POSITIVE LOGITS
    jsxFileName
    0.46
     Plummer
    0.41
    unic
    0.40
    Gemeinden
    0.39
    biet
    0.39
    Scenario
    0.38
    setupUi
    0.37
     sei
    0.36
    Pn
    0.36
    omin
    0.36
    Act Density 0.537%

    No Known Activations