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

    Neuronpedia

    INDEX
    Explanations

    special characters or formatting elements typically found in data representations or scientific texts

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

    units of time and measurement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    -0.42
    -
    -0.39
      
    -0.39
    The
    -0.36
    "
    -0.35
    代
    -0.35
    begin
    -0.35
    _
    -0.35
     ,
    -0.34
    ’
    -0.34
    POSITIVE LOGITS
     للاسماء
    0.92
     gynhyrchwyd
    0.86
    iſen
    0.84
     ujednoznacz
    0.84
     Administrativna
    0.83
     الحره
    0.83
    windowFixed
    0.83
    OGND
    0.82
     Comprometido
    0.81
     فريبيس
    0.81
    Act Density 0.430%

    No Known Activations