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

    Neuronpedia

    INDEX
    Explanations

    concept explanation, map, or art

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ки
    1.05
     can
    0.96
    ے
    0.94
    ли
    0.94
     выпол
    0.90
    なっている
    0.90
    な
    0.90
    言語
    0.89
    اک
    0.88
    ές
    0.86
    POSITIVE LOGITS
    0
    1.66
    d
    1.42
    u
    1.41
    r
    1.41
    st
    1.37
    b
    1.29
    p
    1.28
    t
    1.23
    et
    1.17
    es
    1.15
    Act Density 0.040%

    No Known Activations