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

    Neuronpedia

    INDEX
    Explanations

    excluding Pakistan and Bangladesh

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    篩
    0.49
    顯示
    0.48
    不太
    0.46
     увеличи
    0.45
     Ừ
    0.44
     ഇന്ന്
    0.44
    displayName
    0.44
    ěru
    0.43
     subtiliter
    0.42
    executor
    0.42
    POSITIVE LOGITS
     melod
    0.54
    '
    0.51
     am
    0.47
     can
    0.47
     go
    0.46
     Bagh
    0.46
     would
    0.46
     nowhere
    0.45
     gur
    0.45
     player
    0.44
    Act Density 0.005%

    No Known Activations