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

    Neuronpedia

    INDEX
    Explanations

    someone

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thing
    0.74
     گی۔
    0.68
    그러
    0.65
    हरू
    0.64
    uolo
    0.64
    Synopsis
    0.63
    ))$.
    0.63
    Thing
    0.62
    RootNamespace
    0.62
    Everyone
    0.62
    POSITIVE LOGITS
     someone
    4.35
     Someone
    4.13
    Someone
    4.00
     somebody
    3.88
    someone
    3.86
     alguém
    3.39
     Somebody
    3.36
     alguien
    3.27
    Somebody
    3.16
     quelqu
    3.05
    Act Density 0.658%

    No Known Activations