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

    Neuronpedia

    INDEX
    Explanations

    just

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     legend
    -0.06
     правильно
    -0.06
     дорог
    -0.06
    에
    -0.06
    //--
    -0.06
    达
    -0.06
    sta
    -0.06
     waivers
    -0.06
     serviços
    -0.06
    iaux
    -0.06
    POSITIVE LOGITS
     Fist
    0.07
     Ellis
    0.07
     fidelity
    0.07
    ?>"
    0.06
    ="#"><
    0.06
     arity
    0.06
    ynet
    0.06
    mutation
    0.06
    typeparam
    0.06
    过程
    0.06
    Act Density 0.125%

    No Known Activations