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

    Neuronpedia

    INDEX
    Explanations

    fine followed by period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ize
    0.91
    ные
    0.91
    ದಲ
    0.83
    '$
    0.82
    IZE
    0.78
    هاي
    0.78
    ية
    0.78
    \)
    0.78
     së
    0.74
    𝘬
    0.74
    POSITIVE LOGITS
    .
    0.64
    ,
    0.64
     כך
    0.63
    abouts
    0.60
    ..
    0.59
     لیکن
    0.58
    suggest
    0.58
    some
    0.57
    Caller
    0.57
    env
    0.56
    Act Density 0.841%

    No Known Activations