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

    Neuronpedia

    INDEX
    Explanations

    names followed by last names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.83
    ,
    0.74
    ed
    0.70
    er
    0.69
    line
    0.66
    es
    0.65
    al
    0.65
    ing
    0.62
    e
    0.62
    0.61
    POSITIVE LOGITS
    Ყ
    1.07
     Announces
    1.04
    chyné
    1.04
    arrerol
    1.03
    詄
    0.99
    Ბ
    0.96
    쮿
    0.94
    <unused1900>
    0.93
    avkhat
    0.93
    Ი
    0.93
    Act Density 0.181%

    No Known Activations