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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating validation or proof of concepts

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

    Sentences containing "prove" or "proven"

    np_acts-logits-general · gemini-2.0-flash

    establishes truth or effectiveness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Geist
    -0.61
    día
    -0.56
    瘩
    -0.56
    OCCURRED
    -0.55
    dataclass
    -0.55
    awtextra
    -0.53
    Controllo
    -0.53
     okuyayım
    -0.53
    dziew
    -0.51
    LikeLike
    -0.50
    POSITIVE LOGITS
     prove
    1.29
     Prove
    1.22
     proves
    1.19
    Prove
    1.16
     proved
    1.14
     proving
    1.13
    prove
    1.00
     Proving
    1.00
     proofs
    0.85
     proven
    0.83
    Act Density 0.170%

    No Known Activations