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

    Neuronpedia

    INDEX
    Explanations

    take

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     نق
    -0.06
     speakers
    -0.06
    老师
    -0.06
     trustees
    -0.06
     independence
    -0.06
    “But
    -0.06
    三个
    -0.06
     risen
    -0.06
    亿元
    -0.06
    .urlopen
    -0.06
    POSITIVE LOGITS
     Org
    0.07
     MUST
    0.07
    (le
    0.07
     RECE
    0.07
     Eff
    0.07
     Perm
    0.06
     listopadu
    0.06
    oom
    0.06
     ‌
    0.06
    EPS
    0.06
    Act Density 0.021%

    No Known Activations