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

    Neuronpedia

    INDEX
    Explanations

    occurrences of mathematical operators and expressions involving dimensions or scales

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

    dimensions like 8x10

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     similarly
    -0.46
    ยนต์
    -0.42
     Wissenschaft
    -0.40
    Distribución
    -0.40
    如下
    -0.39
     gehad
    -0.39
    aronder
    -0.39
     Demokratie
    -0.39
     mít
    -0.39
     Similarly
    -0.38
    POSITIVE LOGITS
    -------
    0.61
    0.56
    AutoScaleMode
    0.56
    RenderAtEndOf
    0.52
    ⭐⭐⭐⭐
    0.50
     AssemblyCulture
    0.47
     gynhyrchwyd
    0.46
    chakra
    0.45
    ϫ
    0.45
    hematical
    0.44
    Act Density 0.062%

    No Known Activations