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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Athens
    -0.07
    cluir
    -0.07
    onte
    -0.06
    ical
    -0.06
    ประโย
    -0.06
     taxing
    -0.06
     cửa
    -0.06
    aje
    -0.06
    getInstance
    -0.06
     هواپیم
    -0.06
    POSITIVE LOGITS
    (chan
    0.07
     utf
    0.07
    _CHANGED
    0.07
    (!
    0.06
    /',
    0.06
    (gulp
    0.06
    elah
    0.06
     /**<
    0.06
     multiplic
    0.06
    >')
    0.06
    Act Density 0.001%

    No Known Activations