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

    Neuronpedia

    INDEX
    Explanations

    09

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dint
    -0.07
    _streams
    -0.07
     dann
    -0.06
    _rl
    -0.06
     बस
    -0.06
    융
    -0.06
     ers
    -0.06
     fasc
    -0.06
    /M
    -0.06
     weighing
    -0.06
    POSITIVE LOGITS
     discriminate
    0.07
    تز
    0.06
    щё
    0.06
    .“↵↵
    0.06
    inoa
    0.06
    --[[
    0.06
     ایت
    0.06
     Isaiah
    0.06
    :YES
    0.06
    Previously
    0.06
    Act Density 0.001%

    No Known Activations