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

    Neuronpedia

    INDEX
    Explanations

    Code license information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itles
    -0.07
     Experienced
    -0.07
    感兴趣的
    -0.07
    寺
    -0.06
     belts
    -0.06
    _iterations
    -0.06
    .setParameter
    -0.06
     CLL
    -0.06
     eta
    -0.06
    生产力
    -0.06
    POSITIVE LOGITS
     Lemma
    0.07
    ColumnsMode
    0.07
     الاس
    0.07
    덩
    0.07
    blah
    0.07
     traction
    0.06
    该校
    0.06
    Obama
    0.06
     Reporting
    0.06
    校长
    0.06
    Act Density 0.000%

    No Known Activations