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

    Neuronpedia

    INDEX
    Explanations

    possessive 's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    1.16
    y
    0.94
    ل
    0.89
     것처럼
    0.81
    ح
    0.79
    ной
    0.74
    os
    0.74
    es
    0.74
    р
    0.72
    ş
    0.68
    POSITIVE LOGITS
    ्स
    0.87
     rampant
    0.81
    汋
    0.80
     Tattha
    0.80
     Jovan
    0.80
    svp
    0.78
     annoying
    0.78
     agonizing
    0.77
    sley
    0.77
     आल्स
    0.77
    Act Density 2.695%

    No Known Activations