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

    Neuronpedia

    INDEX
    Explanations

    even slightly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     продъл
    0.49
    កំព
    0.49
     Cruiser
    0.47
     cruising
    0.45
     Kontak
    0.44
     Patreon
    0.44
     Expenses
    0.44
     continue
    0.44
     gren
    0.44
     Kyrie
    0.43
    POSITIVE LOGITS
    エット
    0.43
    віда
    0.42
    ooter
    0.42
     [](
    0.41
     клеток
    0.41
    }$.)
    0.41
     سائٹ
    0.40
    エ
    0.39
    achtige
    0.38
    ogenous
    0.38
    Act Density 0.012%

    No Known Activations