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

    Neuronpedia

    INDEX
    Explanations

    actions directed at them

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mselves
    0.50
     zichzelf
    0.47
    自己在
    0.40
     eponymous
    0.40
     都
    0.40
     fazem
    0.40
     sich
    0.38
     fanno
    0.38
    自己
    0.37
     Pilgrim
    0.37
    POSITIVE LOGITS
     them
    2.03
     ihnen
    2.02
     त्यांना
    1.98
    them
    1.88
    他们
    1.85
     тях
    1.85
     அவர்களை
    1.84
     onların
    1.84
     них
    1.82
    他們
    1.82
    Act Density 0.016%

    No Known Activations