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

    Neuronpedia

    INDEX
    Explanations

    html head tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mechan
    0.92
    Idi
    0.89
    Juni
    0.86
    គឺ
    0.85
    Eric
    0.84
    История
    0.83
     trei
    0.80
     निर्दिष्ट
    0.79
    Wenn
    0.79
    если
    0.78
    POSITIVE LOGITS
     barred
    0.82
     predeceased
    0.82
     Admission
    0.78
    ricted
    0.78
     victim
    0.74
     wait
    0.73
     uphill
    0.73
     grim
    0.73
     areas
    0.72
     Mem
    0.72
    Act Density 0.094%

    No Known Activations