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

    Neuronpedia

    INDEX
    Explanations

    So

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ებისა
    -0.09
    そして
    -0.09
     anderes
    -0.08
     ಮತ್ತು
    -0.08
     denna
    -0.08
    ისა
    -0.08
     anderer
    -0.08
     এবং
    -0.08
     և
    -0.08
     وهل
    -0.08
    POSITIVE LOGITS
     data
    0.09
    ="?
    0.08
    数据
    0.08
     समाधान
    0.07
    .data
    0.07
     solutions
    0.07
     oplossingen
    0.07
     is
    0.07
    _w
    0.07
    atiek
    0.07
    Act Density 0.038%

    No Known Activations