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

    Neuronpedia

    INDEX
    Explanations

    political pressures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    人才
    0.49
    ITTER
    0.47
    按
    0.46
    ेटा
    0.45
    보다
    0.45
     binoculars
    0.44
    数
    0.44
    날
    0.44
    摊
    0.44
    当たり
    0.43
    POSITIVE LOGITS
    setIs
    0.58
    ien
    0.52
    uk
    0.50
     ବ
    0.47
    lil
    0.45
    attiyam
    0.45
    ırl
    0.45
     leurs
    0.44
     وإ
    0.44
     þat
    0.44
    Act Density 0.000%

    No Known Activations