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

    Neuronpedia

    INDEX
    Explanations

    naturally occurring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    絟
    0.43
     Landmarks
    0.42
     gati
    0.39
    ناه
    0.38
     مزاح
    0.38
    咿
    0.38
     दोषी
    0.38
    蛄
    0.37
     Garth
    0.37
     speedometer
    0.37
    POSITIVE LOGITS
     occurring
    0.94
    occurring
    0.84
     occurs
    0.80
     occurrence
    0.75
     occur
    0.74
     ocor
    0.73
     occuring
    0.72
    occur
    0.72
    Occurrence
    0.69
     ocorr
    0.68
    Act Density 0.005%

    No Known Activations