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

    Neuronpedia

    INDEX
    Explanations

    post office

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    1.91
    ので
    1.87
    ğ
    1.83
     thumbs
    1.83
     nutrit
    1.81
    сім
    1.80
    ñ
    1.79
    𝐠
    1.77
    an
    1.74
    ตรฐาน
    1.71
    POSITIVE LOGITS
    কেলে
    1.78
    র
    1.77
    ك
    1.76
    ]]);
    1.75
     דבר
    1.72
    amanho
    1.70
    被迫
    1.70
    ጨማሪ
    1.63
    然後
    1.61
     itertools
    1.61
    Act Density 0.000%

    No Known Activations