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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and terms related to probability distributions and random variables

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

    with [related concepts]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Amicalement
    -0.47
    AppendLine
    -0.46
    maketitle
    -0.44
    (!__
    -0.43
    transQ
    -0.43
    xffffff
    -0.42
     Tat
    -0.42
     ppb
    -0.40
     boto
    -0.40
    lateinit
    -0.40
    POSITIVE LOGITS
     whose
    0.72
    whose
    0.67
     cuyo
    0.66
     cujo
    0.64
     تضيفلها
    0.63
     cuja
    0.62
    >({
    0.59
     cuya
    0.58
     whofe
    0.56
     cuyos
    0.55
    Act Density 0.134%

    No Known Activations