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

    Neuronpedia

    INDEX
    Explanations

    Important Notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     materialize
    0.80
    你在
    0.74
    making
    0.71
    s
    0.67
     making
    0.67
     starts
    0.67
     taking
    0.67
     shall
    0.67
     your
    0.66
     तयार
    0.64
    POSITIVE LOGITS
     note
    2.36
     Note
    2.31
    Note
    2.11
    note
    1.92
     NOTE
    1.91
    NOTE
    1.76
     notes
    1.67
     noted
    1.66
     noting
    1.65
     Notes
    1.62
    Act Density 0.699%

    No Known Activations