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

    Neuronpedia

    INDEX
    Explanations

    newest followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    1.23
    f
    1.16
    n
    1.15
    de
    1.14
    ק
    1.13
    to
    1.11
    s
    1.10
    the
    1.09
    t
    1.08
    ।
    1.08
    POSITIVE LOGITS
     largos
    1.11
    的
    1.06
    '
    1.05
     newest
    1.04
     pequeños
    1.02
     pequenos
    1.00
    /
    1.00
    의
    1.00
    দের
    1.00
     importantes
    0.97
    Act Density 0.004%

    No Known Activations