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

    Neuronpedia

    INDEX
    Explanations

    on-screen instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    付费
    -0.07
    нят
    -0.07
     jo
    -0.07
    czas
    -0.07
     IoT
    -0.06
     Czech
    -0.06
     roulette
    -0.06
     Lyons
    -0.06
     contiene
    -0.06
    涅
    -0.06
    POSITIVE LOGITS
     Redistribution
    0.07
    给你
    0.07
     הבע
    0.07
    _Ass
    0.07
    品尝
    0.07
    string
    0.07
    -string
    0.07
    磔
    0.06
     человека
    0.06
     backgrounds
    0.06
    Act Density 0.024%

    No Known Activations