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

    Neuronpedia

    INDEX
    Explanations

    filler words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     právo
    -0.07
    -Clause
    -0.06
    遍
    -0.06
     Site
    -0.06
    罪
    -0.06
    这种
    -0.06
    .pad
    -0.06
    工程
    -0.06
    Attached
    -0.06
     Pets
    -0.06
    POSITIVE LOGITS
     uh
    0.09
     Um
    0.08
     um
    0.07
    Um
    0.07
    eptal
    0.07
     armor
    0.07
     heck
    0.07
    xffffff
    0.07
     erm
    0.06
    urnal
    0.06
    Act Density 0.007%

    No Known Activations