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

    Neuronpedia

    INDEX
    Explanations

    programming concepts related to data storage and message structures

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

    field and fixed types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    -0.39
    <eos>
    -0.38
     a
    -0.35
     “
    -0.34
    -
    -0.33
     or
    -0.32
     pass
    -0.30
     ‘
    -0.29
     far
    -0.29
    r
    -0.29
    POSITIVE LOGITS
    FunctionFlags
    0.96
     للاسماء
    0.95
     informée
    0.93
     المعيارى
    0.93
    səhifə
    0.90
     nahilalakip
    0.89
    IsContent
    0.89
     Signalez
    0.88
    AndEndTag
    0.88
    OGND
    0.86
    Act Density 0.230%

    No Known Activations