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

    Neuronpedia

    INDEX
    Explanations

    stable diffusion, simulate, migraine, SIM card, profiling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    1.38
     with
    1.19
     has
    1.16
     and
    1.15
     you
    1.09
     on
    1.08
     for
    0.94
     or
    0.93
     from
    0.92
    ia
    0.92
    POSITIVE LOGITS
    й
    1.11
    4
    1.08
    在
    1.06
    рів
    1.03
    ние
    1.02
    8
    1.02
    lere
    1.00
    ز
    1.00
    م
    0.99
    6
    0.98
    Act Density 0.123%

    No Known Activations