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

    Neuronpedia

    INDEX
    Explanations

    Cyrillic text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dataset
    -0.07
     mohou
    -0.07
    하는
    -0.06
     flag
    -0.06
    Senior
    -0.06
    stime
    -0.06
     Hon
    -0.06
     halten
    -0.06
    AUT
    -0.06
    /rules
    -0.06
    POSITIVE LOGITS
    )");
↵
    0.07
     Doğum
    0.06
     curr
    0.06
    );?>↵
    0.06
    ове
    0.06
    })();
    0.06
    (Audio
    0.06
    &q
    0.06
     kommt
    0.06
    )index
    0.06
    Act Density 0.045%

    No Known Activations