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

    Neuronpedia

    INDEX
    Explanations

    code/citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     evacuate
    -0.07
    Colorado
    -0.07
     Crypto
    -0.06
    灭火
    -0.06
    (G
    -0.06
     amort
    -0.06
     '{"
    -0.06
     NumberOf
    -0.06
     deceived
    -0.06
    那些
    -0.06
    POSITIVE LOGITS
    ｻ
    0.08
    赁
    0.07
    연구
    0.07
    с
    0.07
     sticks
    0.07
    acente
    0.07
    ỵ
    0.07
    зи
    0.07
    ('&
    0.07
    dance
    0.07
    Act Density 0.031%

    No Known Activations