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

    Neuronpedia

    INDEX
    Explanations

    encoding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ющего
    -0.08
     Edison
    -0.08
     μεγάλο
    -0.08
     વરસાદ
    -0.08
    куля
    -0.08
     rains
    -0.07
     ekolog
    -0.07
     Ethan
    -0.07
    િયા
    -0.07
    大发电
    -0.07
    POSITIVE LOGITS
    hei
    0.08
     weighting
    0.07
    ary
    0.07
    アル
    0.07
     blitt
    0.07
     mer
    0.07
    Weight
    0.07
     홈페이지
    0.07
     weight
    0.07
    ಗೆ
    0.07
    Act Density 0.000%

    No Known Activations