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

    Neuronpedia

    INDEX
    Explanations

    optical gratings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pillars
    -0.07
    Alabama
    -0.07
     návrh
    -0.06
     Nietzsche
    -0.06
     hồ
    -0.06
    association
    -0.06
     endanger
    -0.06
    ;*/↵
    -0.06
    폭
    -0.06
     vítěz
    -0.06
    POSITIVE LOGITS
     distinctions
    0.08
     distinction
    0.07
    GI
    0.07
    �
    0.07
    ing
    0.07
     LOGGER
    0.07
     Crest
    0.07
     Cary
    0.07
     mint
    0.07
     Weiner
    0.07
    Act Density 0.001%

    No Known Activations