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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and measurements related to data storage and processing capacities

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

    large numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.50
     OnEnable
    -0.38
     poésie
    -0.37
     bapt
    -0.36
     vocales
    -0.36
    Życiorys
    -0.36
     Arzt
    -0.35
    ม่
    -0.35
     sirena
    -0.35
     suger
    -0.35
    POSITIVE LOGITS
    llion
    0.77
     trillion
    0.71
    billion
    0.63
     triliun
    0.57
    sizeCache
    0.56
     miliardi
    0.54
     billions
    0.54
    million
    0.53
     Billion
    0.52
     milliard
    0.51
    Act Density 0.024%

    No Known Activations