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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical operations or terms

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

    Mahathir or Mahajan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MemoryWarning
    -0.59
    újo
    -0.54
     Arma
    -0.54
    belea
    -0.52
    balleur
    -0.52
    Попис
    -0.49
    Packard
    -0.48
    ContentAlignment
    -0.47
     propOrder
    -0.47
     thiệu
    -0.47
    POSITIVE LOGITS
     Maha
    1.76
    Maha
    1.60
     maha
    1.09
    maha
    1.03
     महा
    0.83
     Moha
    0.61
    setMax
    0.58
    maxsize
    0.56
    MaxSize
    0.56
    maxSize
    0.55
    Act Density 0.003%

    No Known Activations