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

    Neuronpedia

    INDEX
    Explanations

    numerical representations or variables, particularly those involving "num" in various contexts

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

    numbers or counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <?
    -0.55
    ever
    -0.54
    eyes
    -0.52
    lifts
    -0.51
    hearts
    -0.51
    light
    -0.50
    embra
    -0.50
    teria
    -0.50
    passe
    -0.49
    pions
    -0.49
    POSITIVE LOGITS
     Num
    1.13
    Num
    1.12
     num
    1.12
    getNum
    1.03
    num
    0.98
     getNum
    0.91
    setNum
    0.90
     nums
    0.88
    NUM
    0.85
    Nums
    0.83
    Act Density 0.005%

    No Known Activations