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

    Neuronpedia

    INDEX
    Explanations

    references to limitations or restrictions

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

    following "limit" or "limited"

    np_acts-logits-general · gemini-2.0-flash

    limited edition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.54
    RSM
    -0.53
    چرا
    -0.53
     criptomonedas
    -0.53
    ッケージ
    -0.52
    ertale
    -0.52
    MessageDigest
    -0.52
    kezik
    -0.51
    iwisata
    -0.50
    +#+
    -0.50
    POSITIVE LOGITS
     Liability
    0.86
     liability
    0.76
     rist
    0.74
     edition
    0.72
     Anzahl
    0.72
    lessly
    0.70
    Liability
    0.68
    limits
    0.68
    liability
    0.68
     number
    0.66
    Act Density 0.191%

    No Known Activations