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

    Neuronpedia

    INDEX
    Explanations

    News/Reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _HT
    -0.06
     ettik
    -0.06
    .bc
    -0.06
     зб
    -0.06
     //_
    -0.06
    ूष
    -0.06
     gé
    -0.06
     Tommy
    -0.06
    .notes
    -0.06
    限
    -0.06
    POSITIVE LOGITS
    ERN
    0.08
     kindly
    0.07
    say
    0.07
     freely
    0.07
     popular
    0.07
    出现
    0.07
    ">'+↵
    0.07
    rible
    0.07
     одну
    0.07
    olare
    0.06
    Act Density 0.000%

    No Known Activations