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

    Neuronpedia

    INDEX
    Explanations

    /LICENSE

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     finely
    -0.08
     hashtag
    -0.08
     shelves
    -0.08
    efa
    -0.07
    姒
    -0.07
    /avatar
    -0.07
    🚄
    -0.07
    혀
    -0.07
    Screens
    -0.07
    importe
    -0.07
    POSITIVE LOGITS
     Katie
    0.07
    ()));↵↵
    0.07
     exam
    0.07
     Thailand
    0.07
    (Error
    0.06
     freedom
    0.06
    泰国
    0.06
    óng
    0.06
    "));↵
    0.06
     Colorado
    0.06
    Act Density 0.000%

    No Known Activations