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

    Neuronpedia

    INDEX
    Explanations

    Technical/instructional text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ragon
    -0.08
    .score
    -0.08
    textbox
    -0.07
    贺
    -0.07
    _bid
    -0.07
    .Pro
    -0.07
    _resolve
    -0.07
    .activities
    -0.07
     agony
    -0.07
    .pro
    -0.07
    POSITIVE LOGITS
     repreh
    0.07
    法规
    0.07
    ฏ
    0.07
    멓
    0.06
    пе
    0.06
    ．
    0.06
     +↵
    0.06
     sıc
    0.06
    经费
    0.06
    有益
    0.06
    Act Density 0.080%

    No Known Activations