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

    Neuronpedia

    INDEX
    Explanations

    third person plural pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mean
    0.82
     quint
    0.82
    QU
    0.79
     kiek
    0.78
     quart
    0.77
    夷
    0.76
     saepe
    0.73
     sometimes
    0.73
     guys
    0.72
     am
    0.72
    POSITIVE LOGITS
    它
    1.19
    它的
    1.10
     Lordships
    1.08
     которому
    1.07
    他们的
    0.99
    ز
    0.99
    atically
    0.98
    രുടെ
    0.98
    Their
    0.98
     它
    0.97
    Act Density 0.057%

    No Known Activations