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

    Neuronpedia

    INDEX
    Explanations

    unordered

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vegetarian
    -0.08
     Farms
    -0.08
    Attorney
    -0.08
     Landing
    -0.08
    Gast
    -0.08
     dishwasher
    -0.08
    Fi
    -0.08
     launched
    -0.08
    тері
    -0.07
     Beef
    -0.07
    POSITIVE LOGITS
     combination
    0.07
    特殊
    0.07
     alg
    0.07
     itertools
    0.07
     pairs
    0.07
     monoch
    0.07
    -message
    0.07
    性质
    0.07
     representation
    0.07
    ประเภท
    0.07
    Act Density 0.004%

    No Known Activations