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

    Neuronpedia

    INDEX
    Explanations

    aforementioned premises

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    скетбол
    0.41
    {
    0.38
    ส่
    0.34
     هيكون
    0.34
    시대
    0.33
    зульта
    0.32
    궐
    0.32
    SequentialGroup
    0.31
    Sebagai
    0.31
    러스
    0.31
    POSITIVE LOGITS
     to
    0.53
     on
    0.43
    in
    0.43
    end
    0.41
    ю
    0.41
    е
    0.41
    s
    0.40
     up
    0.40
     don
    0.40
    of
    0.39
    Act Density 0.000%

    No Known Activations