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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     transforming
    -0.07
    app
    -0.07
    Skills
    -0.07
    rain
    -0.07
     )↵↵↵
    -0.07
    _eg
    -0.07
    潍
    -0.07
     diet
    -0.06
    istro
    -0.06
    ste
    -0.06
    POSITIVE LOGITS
    文献
    0.08
     Authentic
    0.07
    了很多
    0.07
    -topic
    0.07
    academic
    0.07
     eagle
    0.07
    람
    0.07
    ked
    0.07
     lawsuits
    0.07
    _exact
    0.07
    Act Density 0.002%

    No Known Activations