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

    Neuronpedia

    INDEX
    Explanations

    people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ोट
    -0.08
     эту
    -0.07
    *>(
    -0.07
     were
    -0.07
     которое
    -0.07
     unrecognized
    -0.07
     приступ
    -0.07
     regulatory
    -0.07
     controversial
    -0.07
    。此
    -0.06
    POSITIVE LOGITS
    .assertIn
    0.07
     slime
    0.07
     steal
    0.07
    ุทร
    0.07
    LOY
    0.07
    PlainOldData
    0.06
    rais
    0.06
    991
    0.06
    mět
    0.06
    0.06
    Act Density 0.140%

    No Known Activations