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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ///////////////////////////////////////////////////////////////////////////////↵
    -0.07
     Through
    -0.07
    EEEE
    -0.07
    datal
    -0.07
    (el
    -0.06
     statistics
    -0.06
     Loop
    -0.06
    inizi
    -0.06
     luggage
    -0.06
    ductory
    -0.06
    POSITIVE LOGITS
    glob
    0.07
     ощ
    0.07
     examiner
    0.06
    -lines
    0.06
    sizeof
    0.06
    мин
    0.06
    ../
    0.06
    stag
    0.06
    대학
    0.06
    react
    0.06
    Act Density 0.145%

    No Known Activations