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

    Neuronpedia

    INDEX
    Explanations

    pip install instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     পশ্চিমবঙ্গের
    0.78
    umpulan
    0.77
     suffisante
    0.76
    oding
    0.73
     Atmosphäre
    0.71
    ungkan
    0.69
    FileLine
    0.68
     -&
    0.68
    葡萄
    0.68
     Į
    0.68
    POSITIVE LOGITS
    0.77
    ↵↵
    0.70
    <0x0D>
    0.69
     яв
    0.67
     cartoon
    0.66
    pliers
    0.65
     hedge
    0.65
    <end_of_image>
    0.63
     sidelined
    0.62
    alt
    0.62
    Act Density 0.014%

    No Known Activations