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

    Neuronpedia

    INDEX
    Explanations

    is no, is a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    拥有
    0.44
    amel
    0.43
     njeg
    0.43
    нија
    0.42
    having
    0.41
    akim
    0.41
    热爱
    0.41
    erves
    0.39
    メラ
    0.38
    صیل
    0.38
    POSITIVE LOGITS
     plenty
    0.61
     कई
    0.58
     a
    0.58
     no
    0.58
     NO
    0.55
     many
    0.54
     আরও
    0.54
     നിരവധി
    0.53
    SO
    0.53
    หลาย
    0.52
    Act Density 0.006%

    No Known Activations