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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    folk
    -0.07
    .dispose
    -0.07
     municipal
    -0.07
    bj
    -0.06
    소개
    -0.06
    ={['
    -0.06
    (Schedulers
    -0.06
    (matches
    -0.06
    负责
    -0.06
     KBS
    -0.06
    POSITIVE LOGITS
     Теп
    0.07
     ))↵↵
    0.07
     Samples
    0.07
     Month
    0.07
    .Large
    0.06
     별
    0.06
    )}↵↵
    0.06
     Stevens
    0.06
    etherlands
    0.06
                ↵↵
    0.06
    Act Density 0.005%

    No Known Activations