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

    Neuronpedia

    INDEX
    Explanations

    Chinese punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /payment
    -0.08
     هایی
    -0.08
    ery
    -0.08
     nesta
    -0.08
     ocz
    -0.08
    KY
    -0.07
    VO
    -0.07
     NC
    -0.07
    vars
    -0.07
    级
    -0.07
    POSITIVE LOGITS
    เกิด
    0.08
    且
    0.08
    0.08
     moreover
    0.08
    ellect
    0.07
    fcntl
    0.07
     Pros
    0.07
    /of
    0.07
    /or
    0.07
     अर्थात
    0.07
    Act Density 0.052%
    No Known Activations