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

    Neuronpedia

    INDEX
    Explanations

    was at an angle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dukkh
    0.44
     unsatisf
    0.40
     ឬ
    0.40
     venting
    0.39
     sputter
    0.39
     filenames
    0.39
     然后
    0.39
     прово
    0.38
     হতাশ
    0.38
     universo
    0.37
    POSITIVE LOGITS
     ZH
    0.46
    Kep
    0.43
     comest
    0.43
    дение
    0.42
    CH
    0.39
    Demand
    0.39
    Changes
    0.38
     Buxton
    0.38
     popular
    0.38
     Hex
    0.37
    Act Density 0.002%

    No Known Activations