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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notations in the text

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

    mathematical expressions and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TProtocol
    -0.45
    ariConfig
    -0.42
     ReactDOM
    -0.40
    appé
    -0.38
     insults
    -0.38
     Espíritu
    -0.38
     disarmament
    -0.37
    PathParam
    -0.37
    worms
    -0.37
    (/
    -0.37
    POSITIVE LOGITS
     kasarigan
    0.77
     intptr
    0.71
     متعلقه
    0.59
    rungsseite
    0.59
    WriteBarrier
    0.50
    อ้างอิง
    0.49
    存于互联网档案馆
    0.48
    awtextra
    0.47
     otomatig
    0.46
    참고
    0.46
    Act Density 0.045%

    No Known Activations