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

    Neuronpedia

    INDEX
    Explanations

    shadow cast on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eager
    1.04
     enk
    0.94
     gazing
    0.90
     wondering
    0.90
     doings
    0.90
    运作
    0.90
     चिंतन
    0.90
     thriving
    0.87
     worship
    0.86
     environs
    0.85
    POSITIVE LOGITS
    ของ
    1.32
     дочери
    1.23
     của
    1.08
     للط
    1.02
     шриф
    1.02
    ของผู้
    1.01
     of
    1.00
    थ
    0.99
     ของ
    0.97
     للف
    0.97
    Act Density 0.157%

    No Known Activations