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

    Neuronpedia

    INDEX
    Explanations

    Darkness, magic, Among Us

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    टी
    0.77
    你
    0.63
    和他
    0.62
     bullshit
    0.59
    ათ
    0.58
    ัน
    0.57
    ول
    0.56
    აბ
    0.56
     introducir
    0.56
    نت
    0.55
    POSITIVE LOGITS
    ють
    0.73
    ்ய
    0.72
    с
    0.71
    in
    0.69
    less
    0.68
    se
    0.67
    скольку
    0.65
    land
    0.65
    s
    0.65
    н
    0.64
    Act Density 0.001%

    No Known Activations