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

    Neuronpedia

    INDEX
    Explanations

    king who

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     decolor
    0.44
     transmitted
    0.43
    transmit
    0.43
    vigor
    0.42
     calmed
    0.40
     unleashed
    0.40
    transform
    0.40
    uminum
    0.39
     transmit
    0.39
    ,
    0.39
    POSITIVE LOGITS
     усі
    0.52
    全て
    0.50
    입니다
    0.50
    澳洲
    0.49
     все
    0.46
     सबै
    0.46
     ใช้
    0.45
    शीर
    0.45
     сотрудников
    0.45
    จ
    0.45
    Act Density 0.015%

    No Known Activations