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

    Neuronpedia

    INDEX
    Explanations

    documentation tags (param, title, description)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    и
    0.53
    ۔
    0.41
    ти
    0.40
     an
    0.39
    ри
    0.39
    Си
    0.37
    是
    0.37
    СФ
    0.37
    Passengers
    0.37
    分为
    0.36
    POSITIVE LOGITS
    kan
    0.36
    на
    0.35
    <0x98>
    0.34
    را
    0.33
     krok
    0.32
    1
    0.32
    ሳሪያ
    0.32
    s
    0.32
     राज्यातील
    0.31
    রা
    0.31
    Act Density 0.003%

    No Known Activations