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

    Neuronpedia

    INDEX
    Explanations

    as this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     因为
    0.33
     如果
    0.32
    ’
    0.31
     当
    0.29
    ระหว่าง
    0.28
     แบ่ง
    0.27
     चूंकि
    0.27
    م
    0.26
    .
    0.26
    ดัง
    0.25
    POSITIVE LOGITS
     it
    0.54
     a
    0.43
    it
    0.39
     we
    0.38
    a
    0.37
     they
    0.37
     he
    0.36
    sembles
    0.34
     opposed
    0.33
     as
    0.33
    Act Density 0.139%

    No Known Activations