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

    Neuronpedia

    INDEX
    Explanations

    news articles/blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     همان
    -0.07
     являются
    -0.06
     rug
    -0.06
     Exactly
    -0.06
     typical
    -0.06
     unc
    -0.06
    	Set
    -0.06
     sudden
    -0.06
     weekday
    -0.06
     Бар
    -0.06
    POSITIVE LOGITS
    omidou
    0.06
    (Sender
    0.06
    eldom
    0.06
    AILY
    0.06
     Ban
    0.06
    ERVED
    0.06
    ações
    0.06
     hike
    0.06
    _trajectory
    0.06
    　　　　　　　　　　
    0.06
    Act Density 0.079%

    No Known Activations