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

    Neuronpedia

    INDEX
    Explanations

    specific scientific and data-related terms or references within a text

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

    P < value in scientific notation

    np_acts-logits-general · gemini-2.0-flash

    SQW treatments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -1.34
    ########.
    -1.23
    __':
    -1.20
     صوتيه
    -1.17
     &___
    -1.16
     Roskov
    -1.14
     HasFactory
    -1.14
     للاسماء
    -1.11
     nakalista
    -1.09
    PreferredItem
    -1.08
    POSITIVE LOGITS
     ...
    0.66
    <eos>
    0.65
    ...
    0.64
     
    0.55
    ↵
    0.54
     "
    0.52
    "
    0.49
     pass
    0.49
    and
    0.49
    en
    0.49
    Act Density 1.128%

    No Known Activations