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

    Neuronpedia

    INDEX
    Explanations

    operative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     musical
    -0.07
     goose
    -0.07
     ACL
    -0.07
     entrepreneurial
    -0.07
     stabbing
    -0.06
     năng
    -0.06
    baru
    -0.06
    ĩnh
    -0.06
     hardwood
    -0.06
    break
    -0.06
    POSITIVE LOGITS
    	finally
    0.07
     disagrees
    0.07
    .clicked
    0.07
     Sure
    0.07
    .telegram
    0.06
    .Down
    0.06
    .slf
    0.06
    .vis
    0.06
    เหมาะ
    0.06
    (cert
    0.06
    Act Density 0.002%

    No Known Activations