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

    Neuronpedia

    INDEX
    Explanations

    social and political movements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    are
    1.42
    i
    1.27
    in
    1.23
    that
    1.22
    p
    1.17
    ö
    1.16
    ite
    1.09
    om
    1.06
    int
    1.06
    。
    1.05
    POSITIVE LOGITS
    ت
    1.45
    т
    1.29
     Movement
    1.16
     movement
    1.13
     encontr
    1.09
    )";
    1.03
    ).$$
    1.02
     powied
    0.99
    Movement
    0.98
     kutoka
    0.98
    Act Density 0.012%

    No Known Activations