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

    Neuronpedia

    INDEX
    Explanations

    listing examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ا۔
    0.53
     നമഃ
    0.51
    সল
    0.48
    ោគ
    0.47
     elementos
    0.47
    vā
    0.46
    Minist
    0.46
    文物
    0.46
    煩
    0.46
    Ȧ
    0.45
    POSITIVE LOGITS
    "
    0.54
     "
    0.52
    )
    0.49
    0.43
     Kne
    0.42
          
    0.42
     US
    0.41
     MIT
    0.41
     Redwood
    0.41
     UI
    0.41
    Act Density 0.007%

    No Known Activations