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

    Neuronpedia

    INDEX
    Explanations

    b words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BF
    1.46
     BC
    1.45
    BC
    1.44
    BD
    1.44
    BS
    1.42
    BP
    1.42
     BS
    1.42
    BM
    1.40
     BD
    1.38
     BF
    1.38
    POSITIVE LOGITS
     bø
    0.72
     봉
    0.68
    บรร
    0.59
    봉
    0.57
     bö
    0.53
     bimod
    0.51
     bä
    0.50
     ब
    0.46
     brou
    0.46
     ব
    0.46
    Act Density 0.022%

    No Known Activations