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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     khối
    -0.07
     CLL
    -0.07
    详
    -0.06
    ичного
    -0.06
     verg
    -0.06
     DAT
    -0.06
    華
    -0.06
     ident
    -0.06
    tom
    -0.06
    KN
    -0.06
    POSITIVE LOGITS
     Jensen
    0.07
    漫
    0.07
    asting
    0.06
     ");↵↵
    0.06
     reconstruct
    0.06
     tossing
    0.06
    xampp
    0.06
    .getProduct
    0.06
     sigh
    0.06
     dokument
    0.06
    Act Density 0.012%

    No Known Activations