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

    Neuronpedia

    INDEX
    Explanations

    mathematical proofs and logic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "-"↵
    -0.09
     Puntland
    -0.08
     esports
    -0.08
    Stake
    -0.08
     infest
    -0.08
     blockchain
    -0.08
     NGOs
    -0.07
    補
    -0.07
    specialchars
    -0.07
     NFTs
    -0.07
    POSITIVE LOGITS
     pedagog
    0.11
     rigor
    0.10
     deriv
    0.09
    !!!!!
    0.09
     rigorous
    0.09
    heat
    0.09
    asy
    0.09
     elegante
    0.08
    heur
    0.08
     proofs
    0.08
    Act Density 0.029%

    No Known Activations