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

    Neuronpedia

    INDEX
    Explanations

    patterns related to quantitative changes or ratios in scientific measurements

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

    quantifying scale with "fold"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.77
     surla
    -0.66
    دانشنامهٔ
    -0.52
     المعيارى
    -0.48
    IntoConstraints
    -0.46
    Демографія
    -0.43
     CallOverrides
    -0.42
    ilibr
    -0.42
    ModelAdmin
    -0.40
     createSlice
    -0.40
    POSITIVE LOGITS
    times
    0.62
     times
    0.59
     倍
    0.57
    Times
    0.53
    倍
    0.52
    UrlResolution
    0.49
     veces
    0.49
     Times
    0.47
     threefold
    0.45
     multiplier
    0.43
    Act Density 0.129%

    No Known Activations