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

    Neuronpedia

    INDEX
    Explanations

    words followed by a or the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     I
    0.37
    {
    0.34
     of
    0.34
    م
    0.31
    ?
    0.30
    I
    0.30
    neys
    0.29
    <
    0.28
    uding
    0.27
    ;
    0.27
    POSITIVE LOGITS
    ６
    0.36
     فونٹ
    0.35
    ａ
    0.34
     prueba
    0.34
     コン
    0.34
    ก
    0.34
    ユー
    0.34
     براي
    0.34
    z
    0.33
     parola
    0.33
    Act Density 0.991%

    No Known Activations