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

    Neuronpedia

    INDEX
    Explanations

    shorts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     visite
    -0.07
     wave
    -0.07
    mas
    -0.06
    Death
    -0.06
    information
    -0.06
    .street
    -0.06
    	Long
    -0.06
     queues
    -0.06
     Intro
    -0.06
    	double
    -0.06
    POSITIVE LOGITS
    ंड
    0.07
     shorts
    0.06
     sept
    0.06
    Honda
    0.06
    πή
    0.06
     Jill
    0.06
     Сер
    0.06
    ΗΝ
    0.06
    ύ
    0.06
     Rice
    0.06
    Act Density 0.006%

    No Known Activations