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

    Neuronpedia

    INDEX
    Explanations

    phrases concerning numerical data and counts

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

    "Number of" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    counting specific quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нез
    -0.47
     saken
    -0.42
    ó
    -0.41
    New
    -0.38
     grá
    -0.38
    SPJ
    -0.38
    Margins
    -0.37
    <eos>
    -0.37
     precios
    -0.36
     correr
    -0.36
    POSITIVE LOGITS
     numberOf
    0.94
     number
    0.86
     repetitions
    0.81
     layers
    0.81
     iterations
    0.79
    ^(@)
    0.78
     simultaneous
    0.78
     getNum
    0.77
    numberOf
    0.76
     Efq
    0.76
    Act Density 0.530%

    No Known Activations