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

    Neuronpedia

    INDEX
    Explanations

    process mapping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    য়াছে
    0.48
     porphy
    0.46
     gennaio
    0.45
     tonnage
    0.44
     অপ্রত্যাশিত
    0.44
     anni
    0.44
     szpital
    0.44
    рга
    0.43
     Jahre
    0.43
     hepatic
    0.42
    POSITIVE LOGITS
    ズル
    0.43
    il
    0.41
     prób
    0.40
     Debit
    0.40
     Brows
    0.38
     ale
    0.38
     Laptop
    0.38
     alent
    0.38
     takt
    0.38
     ad
    0.38
    Act Density 0.005%

    No Known Activations