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

    Neuronpedia

    INDEX
    Explanations

    before/after

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '">
    0.34
    ‬‬
    0.33
    .}
    0.33
     Beispiel
    0.32
     Andere
    0.32
    .},
    0.32
    >",
    0.31
    .</
    0.31
    Teacher
    0.31
    Give
    0.30
    POSITIVE LOGITS
    स्तक
    0.36
    상은
    0.33
    rasında
    0.32
    陆续
    0.30
    상이
    0.29
    市场的
    0.29
     releg
    0.28
    甚至是
    0.28
    इल
    0.28
     searing
    0.28
    Act Density 0.020%

    No Known Activations