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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     соответствии
    -0.07
    گ
    -0.07
    员
    -0.06
     процесс
    -0.06
    yet
    -0.06
     zer
    -0.06
    .learn
    -0.06
    hu
    -0.06
    struments
    -0.06
    -0.06
    POSITIVE LOGITS
    wise
    0.06
     Vanderbilt
    0.06
    Appending
    0.06
    inery
    0.06
     dims
    0.06
    にして
    0.06
     Socket
    0.06
     Outdoor
    0.06
    張
    0.06
    िसस
    0.06
    Act Density 0.002%

    No Known Activations