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

    Neuronpedia

    INDEX
    Explanations

    significant quantitative measures or statistics in a given context

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

    Follows numbers or special characters

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Normdatei
    -1.12
    NUMX
    -1.03
     '\\;'
    -1.02
     تضيفلها
    -1.01
     HasFactory
    -0.98
    neſs
    -0.95
     iſt
    -0.93
     AttributeSet
    -0.93
     يتيمه
    -0.91
     Мексичка
    -0.89
    POSITIVE LOGITS
    ↵↵
    0.98
    <eos>
    0.75
     &
    0.67
    ↵
    0.67
     •
    0.66
     
    0.66
    !
    0.65
    @
    0.64
    •
    0.61
    \\
    0.60
    Act Density 0.116%

    No Known Activations