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

    Neuronpedia

    INDEX
    Explanations

    like trying to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conundrum
    0.44
    ковые
    0.42
    ďaka
    0.41
    োধী
    0.41
     rectal
    0.41
    мпаваць
    0.41
     unquestionably
    0.40
     polysaccharide
    0.40
    時間は
    0.40
     midrange
    0.39
    POSITIVE LOGITS
    یو
    0.48
    qualification
    0.44
    스터
    0.44
    لی
    0.42
    ^{*}}\
    0.42
     업데이트
    0.42
    난
    0.42
    단
    0.41
    ان
    0.41
     caus
    0.40
    Act Density 0.001%

    No Known Activations