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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    にと
    -0.07
    ста
    -0.07
    dbh
    -0.06
    .redirect
    -0.06
    unity
    -0.06
     Damien
    -0.06
    phin
    -0.06
    520
    -0.06
     qué
    -0.06
    先生
    -0.06
    POSITIVE LOGITS
     appears
    0.07
     search
    0.06
     Removes
    0.06
     MacDonald
    0.06
    /*
↵
    0.06
     ];
↵
    0.06
    -follow
    0.06
     někdy
    0.06
     appeared
    0.06
    DECLARE
    0.06
    Act Density 0.054%

    No Known Activations