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

    Neuronpedia

    INDEX
    Explanations

    gargle with salt water

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arin
    0.75
    il
    0.69
    ate
    0.66
    laş
    0.66
    lių
    0.66
    all
    0.65
    alla
    0.64
    Los
    0.62
    alid
    0.62
    and
    0.61
    POSITIVE LOGITS
    有
    0.83
    وي
    0.69
    ر
    0.69
    聪
    0.68
    ولي
    0.68
    后
    0.66
    前後
    0.66
    ِي
    0.65
    不
    0.64
    ва
    0.64
    Act Density 0.001%

    No Known Activations