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

    Neuronpedia

    INDEX
    Explanations

    specific quotation marks and punctuation in text

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

    names in quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.58
     ModelExpression
    -0.50
    -0.47
    featureID
    -0.46
    randomUUID
    -0.45
    ViewFeatures
    -0.45
    adaptiveStyles
    -0.45
    Excess
    -0.43
     Excess
    -0.43
    üyada
    -0.42
    POSITIVE LOGITS
    Зноскі
    0.45
    Спасылкі
    0.44
     disponibilités
    0.42
     呢
    0.36
    rceil
    0.36
    reinterpret
    0.35
    łbym
    0.34
    rfloor
    0.34
    სქოლიო
    0.34
    thoven
    0.34
    Act Density 0.095%

    No Known Activations