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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     노
    -0.07
     réfé
    -0.07
    	buf
    -0.07
     الأخرى
    -0.07
     dept
    -0.07
     topped
    -0.06
    .parsers
    -0.06
    mtx
    -0.06
     cuc
    -0.06
    上榜
    -0.06
    POSITIVE LOGITS
    DAL
    0.07
    NZ
    0.07
    =*
    0.07
    -component
    0.07
    /load
    0.07
     especially
    0.07
    .export
    0.07
    ako
    0.07
    o
    0.07
     Gibraltar
    0.07
    Act Density 0.001%

    No Known Activations