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

    Neuronpedia

    INDEX
    Explanations

    quantifiers followed by us

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     These
    0.56
    これらの
    0.52
    These
    0.50
     Эти
    0.48
    these
    0.48
     these
    0.46
     эти
    0.46
     thefe
    0.44
    Эти
    0.44
     quei
    0.43
    POSITIVE LOGITS
     us
    1.07
     everyone
    0.99
     нас
    0.95
    Everyone
    0.92
    everyone
    0.83
     everybody
    0.80
     Everyone
    0.80
    大家
    0.79
    ทุกคน
    0.77
     iedereen
    0.75
    Act Density 0.011%

    No Known Activations