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

    Neuronpedia

    INDEX
    Explanations

    see

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     entreprises
    -0.06
     За
    -0.06
     ให
    -0.06
    的问题
    -0.06
     Από
    -0.06
     non
    -0.06
    ->{'
    -0.06
     Та
    -0.06
    Unicode
    -0.06
    ющей
    -0.06
    POSITIVE LOGITS
     ráno
    0.07
     öden
    0.06
    _show
    0.06
     clums
    0.06
     limp
    0.06
    rior
    0.06
     stead
    0.06
    gren
    0.06
     burdens
    0.06
    Brad
    0.06
    Act Density 0.017%

    No Known Activations