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

    Neuronpedia

    INDEX
    Explanations

    repetitive numerical patterns and timestamps

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

    timestamps, code separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bewegungen
    -0.41
     nôtre
    -0.38
    łaszcza
    -0.38
     recientemente
    -0.38
     bosques
    -0.37
     mourut
    -0.37
     Infór
    -0.37
     repetir
    -0.37
    ciorys
    -0.36
     apparaître
    -0.36
    POSITIVE LOGITS
     يتيمه
    0.67
     للاسماء
    0.63
    +#+#
    0.63
    IContainer
    0.63
    存于互联网档案馆
    0.61
    principalTable
    0.59
    thâu
    0.59
     وتسجيلات
    0.58
     <<<<<<<<<<<<<<
    0.58
    SequentialGroup
    0.58
    Act Density 0.016%

    No Known Activations