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

    Neuronpedia

    INDEX
    Explanations

    technical, foreign, or specific names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    也
    0.46
    also
    0.46
    ুস
    0.46
    弥
    0.44
    append
    0.44
    ও
    0.43
    ថា
    0.43
    ো
    0.43
    ন্দ
    0.42
    也有
    0.41
    POSITIVE LOGITS
     jedno
    0.52
     overfitting
    0.48
     σήμερα
    0.47
    musik
    0.46
     abon
    0.45
    reon
    0.45
     صارفین
    0.45
     Landon
    0.45
    rène
    0.45
     Auguste
    0.44
    Act Density 0.004%

    No Known Activations