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

    Neuronpedia

    INDEX
    Explanations

    prefixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     memories
    -0.08
    erti
    -0.08
    ~,
    -0.07
     pins
    -0.07
    erral
    -0.07
    Rendering
    -0.07
     その他
    -0.07
    -0.06
     enables
    -0.06
    طور
    -0.06
    POSITIVE LOGITS
     emit
    0.06
     عز
    0.06
     furn
    0.06
     Mueller
    0.06
     rost
    0.06
     tăng
    0.06
    Ст
    0.06
    kish
    0.06
    (()
    0.06
     coi
    0.06
    Act Density 0.168%

    No Known Activations