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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating superiority or excellence

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

    superlative quality or domain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Borrow
    -0.35
     Under
    -0.34
     timing
    -0.32
     staggering
    -0.29
     Kle
    -0.29
     ஆ
    -0.29
     engaging
    -0.29
     Unter
    -0.29
     some
    -0.29
    FIG
    -0.29
    POSITIVE LOGITS
    تقاوى
    0.91
    Personendaten
    0.76
    0.69
    TagMode
    0.68
     EconPapers
    0.67
    styleType
    0.66
    BeginContext
    0.66
    IntoConstraints
    0.63
    TargetException
    0.63
    Reputation
    0.60
    Act Density 0.022%

    No Known Activations