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

    Neuronpedia

    INDEX
    Explanations

    quantitative measures and large numerical values

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

    numbers and quantities with units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     continuidad
    -0.40
     cuantos
    -0.39
     auroit
    -0.38
     pouvoit
    -0.36
     málo
    -0.35
     pelear
    -0.35
     tolerancia
    -0.34
     toalla
    -0.34
     respetar
    -0.34
    Derbyniad
    -0.34
    POSITIVE LOGITS
    ConstraintMaker
    0.64
    Parcelize
    0.53
     {},
    0.50
    utilisons
    0.49
     Wikimedijinoj
    0.49
    ✨:
    0.49
    parseLong
    0.48
    posedge
    0.48
     demo
    0.48
    :✨
    0.48
    Act Density 0.031%

    No Known Activations