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

    Neuronpedia

    INDEX
    Explanations

    searching

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    еви
    -0.07
    ’.↵↵
    -0.07
     Hakk
    -0.06
    Eat
    -0.06
    만남
    -0.06
     Surround
    -0.06
     نوشته
    -0.06
    裕
    -0.06
    Main
    -0.06
     Saf
    -0.06
    POSITIVE LOGITS
     anatom
    0.08
     aque
    0.07
    ieur
    0.07
     Flickr
    0.06
     una
    0.06
    weights
    0.06
     traj
    0.06
    (close
    0.06
    _weight
    0.06
    _RESOLUTION
    0.06
    Act Density 0.015%

    No Known Activations