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

    Neuronpedia

    INDEX
    Explanations

    family and father names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hereditary
    0.43
     held
    0.43
     became
    0.42
     holder
    0.42
     urn
    0.40
     had
    0.40
     brother
    0.40
     proton
    0.39
     dwellings
    0.39
     inscribed
    0.39
    POSITIVE LOGITS
     மிசோ
    0.55
    르
    0.54
    owaniu
    0.50
    ्ता
    0.50
     парамет
    0.49
    ayla
    0.47
    글
    0.46
    avkh
    0.46
     మరియు
    0.46
    갑습니다
    0.45
    Act Density 0.020%

    No Known Activations