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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arguments
    -0.07
     Emperor
    -0.07
    ceptions
    -0.07
     balcon
    -0.06
     Mais
    -0.06
    Ha
    -0.06
    experience
    -0.06
    _areas
    -0.06
     Laure
    -0.06
     dwelling
    -0.06
    POSITIVE LOGITS
    _exists
    0.07
     sebuah
    0.06
     وصل
    0.06
     in
    0.06
     ""),↵
    0.06
    .WaitFor
    0.06
    ','.
    0.06
    imuth
    0.06
     Saudis
    0.06
     downwards
    0.06
    Act Density 0.061%

    No Known Activations