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

    Neuronpedia

    INDEX
    Explanations

    categories and status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hasonló
    0.43
     clásica
    0.43
     geochemical
    0.43
    几十
    0.42
     ধারণা
    0.41
    前者
    0.41
     Çünkü
    0.40
     আকাঙ্
    0.40
    因为
    0.39
    致命
    0.39
    POSITIVE LOGITS
    v
    0.46
    end
    0.43
    V
    0.42
    st
    0.41
    in
    0.41
    ir
    0.40
    ul
    0.40
    _
    0.40
     V
    0.40
    un
    0.39
    Act Density 0.019%

    No Known Activations