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

    Neuronpedia

    INDEX
    Explanations

    Russian

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OTE
    -0.07
    ragment
    -0.07
     slu
    -0.06
    پ
    -0.06
    lane
    -0.06
    ENDED
    -0.06
    ação
    -0.06
    ゥ
    -0.06
    .median
    -0.06
    	style
    -0.06
    POSITIVE LOGITS
     Did
    0.07
     stochastic
    0.07
     Misc
    0.07
     такие
    0.07
    athlete
    0.07
    roy
    0.06
     таким
    0.06
    feit
    0.06
     такой
    0.06
    082
    0.06
    Act Density 0.002%

    No Known Activations