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

    Neuronpedia

    INDEX
    Explanations

    correctness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ellers
    -0.07
    294
    -0.06
    賣
    -0.06
    >())↵
    -0.06
     применя
    -0.06
    ेबस
    -0.06
    affer
    -0.06
    217
    -0.06
    .Now
    -0.06
    adığ
    -0.06
    POSITIVE LOGITS
     Ebony
    0.07
     statistically
    0.07
    ;


↵
    0.07
     Wort
    0.06
     reducing
    0.06
     bra
    0.06
     ebony
    0.06
     �
    0.06
    (expected
    0.06
     pageTitle
    0.06
    Act Density 0.022%

    No Known Activations