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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and operations related to dimensions and ratios

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

    Code involving canvas dimensions/coordinates

    np_acts-logits-general · gemini-2.0-flash

    two, deux, 두

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    One
    -0.61
    one
    -0.60
     one
    -0.57
     One
    -0.54
     propOrder
    -0.47
    First
    -0.46
     First
    -0.44
     yksi
    -0.42
    imp
    -0.42
     ONE
    -0.42
    POSITIVE LOGITS
     two
    0.84
     متعلقه
    0.83
     deux
    0.80
    twimg
    0.79
    OGND
    0.78
    TWO
    0.77
    __*/
    0.74
     두
    0.73
    deux
    0.70
    Deux
    0.69
    Act Density 0.587%

    No Known Activations