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

    Neuronpedia

    INDEX
    Explanations

    walk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aters
    -0.07
     ist
    -0.06
     MENU
    -0.06
    Ub
    -0.06
    Depth
    -0.06
     livre
    -0.06
     Они
    -0.06
    >Login
    -0.06
     Наз
    -0.06
     Notification
    -0.06
    POSITIVE LOGITS
    怎么
    0.07
     {*}
    0.07
    (LED
    0.07
     Hispanics
    0.07
    (inputStream
    0.07
    är
    0.07
     collusion
    0.06
    :↵↵↵
    0.06
    сыл
    0.06
     random
    0.06
    Act Density 0.009%

    No Known Activations