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

    Neuronpedia

    INDEX
    Explanations

    system

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     في
    -0.07
     operator
    -0.06
    \uff
    -0.06
     inhabitants
    -0.06
    Selection
    -0.06
     pylab
    -0.06
    ard
    -0.06
     adress
    -0.06
    界
    -0.06
    shuffle
    -0.06
    POSITIVE LOGITS
     Rencontre
    0.06
    ilet
    0.06
    _USER
    0.06
     Ou
    0.06
    /language
    0.06
     placed
    0.06
    ，不
    0.05
     Bí
    0.05
     الذ
    0.05
     BG
    0.05
    Act Density 0.008%

    No Known Activations