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

    Neuronpedia

    INDEX
    Explanations

    prior to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ه
    0.68
     practiced
    0.56
     impressed
    0.55
    ৯
    0.53
     incredibly
    0.52
    ת
    0.52
     amazingly
    0.52
    E
    0.52
     behaved
    0.51
     rallied
    0.51
    POSITIVE LOGITS
    ôn
    0.55
    ায়
    0.52
    vät
    0.50
     उद्देश्य
    0.49
     ऐतिहासिक
    0.47
     tutkim
    0.47
     प्रस्ताव
    0.47
    ôm
    0.47
     tathapi
    0.46
    gomery
    0.46
    Act Density 0.000%

    No Known Activations