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

    Neuronpedia

    INDEX
    Explanations

    map

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sutton
    -0.07
     你
    -0.07
     Book
    -0.07
     enjoyment
    -0.07
    xFFF
    -0.07
     vengeance
    -0.07
     unravel
    -0.06
    }"↵
    -0.06
    UserData
    -0.06
    -place
    -0.06
    POSITIVE LOGITS
    |unique
    0.06
    _INTR
    0.06
    yahoo
    0.06
    jte
    0.06
     compareTo
    0.06
    Services
    0.06
    の一
    0.06
    ázky
    0.06
    !;↵
    0.06
    Lt
    0.06
    Act Density 0.002%

    No Known Activations