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

    Neuronpedia

    INDEX
    Explanations

    Titles and names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    利用
    -0.07
    _slow
    -0.06
     engr
    -0.06
    'in
    -0.06
    Square
    -0.06
     gram
    -0.06
    _str
    -0.06
    319
    -0.06
     leg
    -0.06
     Recommend
    -0.06
    POSITIVE LOGITS
    �
    0.07
     fø
    0.07
     Би
    0.06
    одейств
    0.06
    ungan
    0.06
     drafts
    0.06
    δος
    0.06
     nouvelle
    0.06
    exemple
    0.06
    инок
    0.06
    Act Density 0.189%

    No Known Activations