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

    Neuronpedia

    INDEX
    Explanations

    answering questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [pos
    -0.07
    -No
    -0.07
    Science
    -0.07
     reassure
    -0.07
    Ten
    -0.06
    (The
    -0.06
    P
    -0.06
    simple
    -0.06
     conceive
    -0.06
     inferred
    -0.06
    POSITIVE LOGITS
     Illustrator
    0.08
    �
    0.07
     이게
    0.07
    'user
    0.07
    وبا
    0.07
    ấm
    0.07
     созда
    0.07
     онл
    0.07
    -Americ
    0.07
     póź
    0.07
    Act Density 0.026%

    No Known Activations