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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts related to probabilities and combinations involving the picking of letters or numbers

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

    probability calculations without replacement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onAnimation
    -0.81
     autorytatywna
    -0.74
     Autorisations
    -0.73
    titleMargin
    -0.73
     verſch
    -0.71
    AsUp
    -0.69
    expandindo
    -0.69
    帖最后由
    -0.68
     CanadaChoose
    -0.68
     Exacts
    -0.68
    POSITIVE LOGITS
    i
    0.44
    e
    0.44
    ↵
    0.42
    k
    0.42
    a
    0.42
    v
    0.41
    I
    0.41
    E
    0.41
    <eos>
    0.40
    se
    0.40
    Act Density 0.002%

    No Known Activations