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

    Neuronpedia

    INDEX
    Explanations

    prefetch and etch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lady
    -0.07
    white
    -0.07
     hữu
    -0.06
     Gaut
    -0.06
    Ed
    -0.06
    pid
    -0.06
    -Am
    -0.06
     mainScreen
    -0.06
    縮
    -0.06
     cử
    -0.06
    POSITIVE LOGITS
     θ
    0.06
    ITS
    0.06
     slugg
    0.06
    eller
    0.06
     PLUS
    0.06
    !!!
    0.06
     testData
    0.06
     regularization
    0.06
     lessons
    0.06
    ifications
    0.06
    Act Density 0.003%

    No Known Activations