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

    Neuronpedia

    INDEX
    Explanations

    unsanitary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    of
    1.30
    ály
    1.05
    一系列
    1.02
    it
    0.99
    它
    0.97
    ंकन
    0.96
    ሶች
    0.95
    ни
    0.93
    рия
    0.92
    一种
    0.92
    POSITIVE LOGITS
    ur
    1.45
     you
    1.37
    8
    1.30
    6
    1.22
    0
    1.13
    7
    1.13
     your
    1.13
     their
    1.09
    3
    1.09
     می
    1.08
    Act Density 0.000%

    No Known Activations