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

    Neuronpedia

    INDEX
    Explanations

    "third", "missing", "boundaries"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     않았
    0.38
    なども
    0.38
     }},
    0.38
    これも
    0.38
    etches
    0.37
    он
    0.36
     इनका
    0.36
     vaccines
    0.36
     ഇവ
    0.36
    ก็ได้
    0.36
    POSITIVE LOGITS
     dritten
    0.45
     totiž
    0.44
     derde
    0.43
     piuttosto
    0.43
     troisième
    0.41
     üçüncü
    0.40
    缺失
    0.39
     fehl
    0.39
     Elise
    0.38
    তৃত
    0.38
    Act Density 0.044%

    No Known Activations