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

    Neuronpedia

    INDEX
    Explanations

    Searching or inability to find

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inning
    -0.09
     Addition
    -0.08
    Addition
    -0.08
     गौर
    -0.08
    abcdefghijkl
    -0.08
    анный
    -0.08
    unnut
    -0.08
     Главное
    -0.08
     Francisco
    -0.07
     toevoeg
    -0.07
    POSITIVE LOGITS
     availability
    0.15
    Availability
    0.14
     Availability
    0.14
     ઉપલબ્ધ
    0.14
     disponibilité
    0.14
     beschikbaar
    0.13
    _available
    0.13
     disponíveis
    0.13
     tersedia
    0.13
     उपलब्ध
    0.13
    Act Density 0.121%

    No Known Activations