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

    Neuronpedia

    INDEX
    Explanations

    QA, English, focus, Anadolu

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gdy
    1.39
    o
    1.21
     Heavenly
    1.13
    ्रो
    1.11
    ूव
    1.11
     Existence
    1.11
     Occurrence
    1.10
     gange
    1.09
     Joystick
    1.08
    ضع
    1.08
    POSITIVE LOGITS
     semper
    1.04
    $,
    1.02
    <bos>
    1.01
     entrees
    1.00
     arable
    0.99
    sung
    0.98
    ન્ડ
    0.97
    contiguous
    0.95
    اسی
    0.95
    yczne
    0.94
    Act Density 0.006%

    No Known Activations