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

    Neuronpedia

    INDEX
    Explanations

    content related to mathematical proofs and their components

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

    proof of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.59
     uſed
    -0.57
    zzleHttp
    -0.54
     fometimes
    -0.53
    SharedCtor
    -0.52
     houſe
    -0.51
     perfons
    -0.50
     gabbana
    -0.50
    ]")]
    -0.50
     Wikispecies
    -0.49
    POSITIVE LOGITS
     proof
    0.52
     proofs
    0.50
    proof
    0.47
     PROOF
    0.43
    Prove
    0.42
    prove
    0.42
    Proof
    0.41
     proving
    0.41
     chứng
    0.40
     Prove
    0.39
    Act Density 0.105%

    No Known Activations