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

    Neuronpedia

    INDEX
    Explanations

    technical or domain-specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ပါတယ်
    0.63
    かもしれませんが
    0.61
     \%$,
    0.60
    と思いますが
    0.59
    %),
    0.55
    !),
    0.55
     уйнагыз
    0.54
    !,
    0.54
    ),[
    0.53
    しますが
    0.51
    POSITIVE LOGITS
    。
    1.40
    ™.
    1.04
    .
    1.04
    ।
    1.02
    ።
    1.02
    *.
    1.01
    ។
    1.00
    +.
    1.00
    ‌.
    0.98
    ۔
    0.98
    Act Density 0.164%

    No Known Activations