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

    Neuronpedia

    INDEX
    Explanations

    specific names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    кован
    0.59
     рубе
    0.57
     criminal
    0.54
    ராக
    0.54
     Dokument
    0.54
    хоро
    0.54
    হার
    0.53
     روشنی
    0.53
     զ
    0.53
     horizonte
    0.53
    POSITIVE LOGITS
    লভ
    0.64
    vib
    0.58
    sov
    0.53
    Viral
    0.52
    蔥
    0.52
    ্লে
    0.51
    Gov
    0.51
    vard
    0.50
    BW
    0.49
    ंधी
    0.49
    Act Density 0.002%

    No Known Activations