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

    Neuronpedia

    INDEX
    Explanations

    give me a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    P
    0.80
    S
    0.79
    B
    0.79
    A
    0.78
    ש
    0.77
    W
    0.74
    D
    0.72
    C
    0.69
    in
    0.64
    ד
    0.63
    POSITIVE LOGITS
     cárc
    0.61
    小组
    0.57
     Unidas
    0.55
    就會
    0.54
     spazio
    0.54
    监狱
    0.54
     josé
    0.53
    nější
    0.53
     ομά
    0.53
     கிழக்கு
    0.53
    Act Density 0.023%

    No Known Activations