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

    Neuronpedia

    INDEX
    Explanations

    word endings: -ness, -ism, -ia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    0.74
    ş
    0.66
    가
    0.63
    อร์
    0.61
     จ
    0.60
    お
    0.59
    िक
    0.58
    gambar
    0.58
    ع
    0.56
    ು
    0.56
    POSITIVE LOGITS
    ,
    0.66
    ;
    0.66
    />}/>
    0.61
    .
    0.61
    ,​
    0.61
    ​.
    0.60
     WARRANTIES
    0.57
    ⁣
    0.54
    .\\
    0.54
    ]).
    0.53
    Act Density 0.072%

    No Known Activations