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

    Neuronpedia

    INDEX
    Explanations

    al

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Succ
    -0.07
     Huff
    -0.07
    半小时
    -0.07
    CCR
    -0.07
    interesting
    -0.07
    许久
    -0.07
    ="?
    -0.07
    snippet
    -0.07
    授信
    -0.07
    !<
    -0.07
    POSITIVE LOGITS
    ()))
    0.08
    registro
    0.07
    .metro
    0.07
     Entire
    0.07
    riday
    0.07
    标注
    0.07
    -re
    0.07
     serum
    0.07
    .mask
    0.07
    utivo
    0.06
    Act Density 0.002%

    No Known Activations