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

    Neuronpedia

    INDEX
    Explanations

    common word sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.61
    Ｅ
    0.52
     table
    0.51
    াস
    0.51
    FTWARE
    0.49
    á
    0.49
    א
    0.48
     wast
    0.47
     cortar
    0.47
     coworkers
    0.47
    POSITIVE LOGITS
     હો
    0.46
     livelli
    0.45
    檔案
    0.43
     श
    0.42
     투
    0.42
     क्रिप्ट
    0.42
     ολο
    0.42
    donation
    0.42
    ring
    0.41
    voice
    0.41
    Act Density 0.000%

    No Known Activations