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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    论文
    -0.06
    critical
    -0.06
     Ninja
    -0.06
     feelings
    -0.06
    expect
    -0.06
    .jd
    -0.06
    w
    -0.06
    _li
    -0.06
    까지
    -0.06
     Tb
    -0.06
    POSITIVE LOGITS
    医疗
    0.07
    BMI
    0.06
    _filled
    0.06
     duration
    0.06
    ENCH
    0.06
     bilg
    0.06
    \param
    0.06
    .wall
    0.06
    .genre
    0.06
     cerr
    0.06
    Act Density 0.041%

    No Known Activations