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

    Neuronpedia

    INDEX
    Explanations

    the letter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     proceeded
    1.02
    нкү
    1.01
     üzeri
    1.00
     consequently
    0.97
     použit
    0.96
     hectares
    0.95
     akár
    0.95
     thrived
    0.95
     kubwa
    0.95
     incluyendo
    0.94
    POSITIVE LOGITS
    с
    1.23
    нг
    1.16
    I
    1.12
    ச
    1.04
    त
    1.02
    త
    0.98
    一样的
    0.96
    {-#
    0.94
    P
    0.94
    ông
    0.93
    Act Density 0.000%

    No Known Activations