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

    Neuronpedia

    INDEX
    Explanations

    decimal numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rus
    -0.07
    ragen
    -0.07
    ugu
    -0.07
    .Split
    -0.07
     YOU
    -0.07
    -update
    -0.06
     twisting
    -0.06
    υγ
    -0.06
     junto
    -0.06
    YOU
    -0.06
    POSITIVE LOGITS
    ///
↵
    0.07
     gören
    0.07
    Při
    0.06
     empresas
    0.06
    0.06
    ]]>
    0.06
    fid
    0.06
     session
    0.06
    ılır
    0.05
     endiş
    0.05
    Act Density 0.033%

    No Known Activations