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

    Neuronpedia

    INDEX
    Explanations

    physical and digital locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    內的
    0.51
    裡的
    0.50
    openList
    0.50
    }");
    0.44
     ઓફ
    0.44
    内的
    0.43
    ర్భ
    0.43
     它
    0.43
     אור
    0.43
     няколко
    0.42
    POSITIVE LOGITS
    .
    0.66
     the
    0.47
    प्रति
    0.47
     dengan
    0.47
     with
    0.46
    ما
    0.46
    ché
    0.46
     suffering
    0.45
    ید
    0.45
    ifrån
    0.44
    Act Density 0.037%

    No Known Activations