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

    Neuronpedia

    INDEX
    Explanations

    training

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    d
    0.49
    ροι
    0.48
    تهم
    0.45
    Î
    0.45
    t
    0.44
    Il
    0.44
    igy
    0.44
    aną
    0.43
    кой
    0.43
    ƴ
    0.43
    POSITIVE LOGITS
     وغ
    0.49
     cancellations
    0.46
     cancels
    0.45
     பின்பற்ற
    0.45
     সীমিত
    0.44
     cancellation
    0.43
     יותר
    0.43
     कक्कड़
    0.43
     inhibits
    0.42
     Optical
    0.41
    Act Density 0.000%

    No Known Activations