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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and special characters used in the text

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

    Characters surrounding parentheses

    np_acts-logits-general · gemini-2.0-flash

    code, math, or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]")]
    -1.25
    =$?
    -1.20
    SBATCH
    -1.18
     للمعارف
    -1.16
     مشين
    -1.16
    AllAfrica
    -1.15
    FTFY
    -1.15
    __':
    -1.15
    expandindo
    -1.12
    ^(@)
    -1.11
    POSITIVE LOGITS
      
    1.11
     ,
    1.08
    and
    1.00
    to
    0.95
       
    0.94
    for
    0.93
    has
    0.91
    in
    0.89
    is
    0.88
    of
    0.84
    Act Density 2.662%

    No Known Activations