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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vidé
    -0.06
    Mongo
    -0.06
     ساعت
    -0.06
     pits
    -0.06
     نيز
    -0.06
     giving
    -0.06
    butt
    -0.06
    셨
    -0.06
    sect
    -0.06
    Regressor
    -0.06
    POSITIVE LOGITS
     La
    0.08
     Choosing
    0.07
    ’on
    0.07
     BFS
    0.07
    今天
    0.06
     Eu
    0.06
    rules
    0.06
    ://
    0.06
    CardContent
    0.06
    :\\
    0.06
    Act Density 0.184%

    No Known Activations