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

    Neuronpedia

    INDEX
    Explanations

    common terms and usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ジョ
    0.48
    ドラ
    0.46
    ポイント
    0.46
    ।
    0.45
    CHEN
    0.44
    グラフ
    0.44
    マー
    0.44
    gios
    0.44
    ラの
    0.44
     выпол
    0.43
    POSITIVE LOGITS
    sense
    0.45
     Lega
    0.44
    تي
    0.42
    نيه
    0.42
    نګه
    0.42
    نې
    0.42
    甯
    0.42
    లన
    0.41
    㑹
    0.41
    రీలు
    0.40
    Act Density 0.000%

    No Known Activations