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

    Neuronpedia

    INDEX
    Explanations

    leads to consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     они
    1.11
     They
    0.92
     saját
    0.91
    We
    0.90
    They
    0.90
     Они
    0.88
     如何
    0.87
     उन्होंने
    0.86
    they
    0.86
     Он
    0.84
    POSITIVE LOGITS
     us
    2.50
     him
    2.03
     them
    2.00
     me
    1.61
    them
    1.43
     нас
    1.35
    him
    1.22
     credence
    1.21
     itself
    1.19
     THEM
    1.14
    Act Density 0.436%

    No Known Activations