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

    Neuronpedia

    INDEX
    Explanations

    f-string messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OTS
    0.70
     WATTS
    0.69
     magnitud
    0.69
     prud
    0.68
    ες
    0.68
    itudes
    0.67
    idine
    0.66
    ேன்
    0.66
     motores
    0.65
    Watts
    0.65
    POSITIVE LOGITS
     Özel
    0.67
    <unused49>
    0.66
    底层
    0.64
     gegenüber
    0.62
    config
    0.60
    Gender
    0.59
    schema
    0.58
     दिर
    0.58
    зі
    0.57
    star
    0.57
    Act Density 0.005%

    No Known Activations