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

    Neuronpedia

    INDEX
    Explanations

    advanced civilizations or artificial intelligence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Хи
    0.89
    ungkin
    0.86
    šit
    0.80
    0.78
     Органи
    0.77
    蛜
    0.75
    šanu
    0.73
    ធ្វ
    0.72
    ផ្តល់
    0.72
    㨁
    0.71
    POSITIVE LOGITS
    -
    0.94
    +
    0.93
     from
    0.84
     by
    0.83
     for
    0.82
     of
    0.82
     version
    0.78
     vs
    0.78
     or
    0.77
     which
    0.73
    Act Density 0.001%

    No Known Activations