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

    Neuronpedia

    INDEX
    Explanations

    business plan or accounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝑟
    1.07
    edly
    1.04
    iyi
    0.97
    𝑡
    0.96
    iant
    0.96
    商品は
    0.95
     वस्तुओं
    0.94
     Tada
    0.93
     جامعة
    0.93
    URA
    0.92
    POSITIVE LOGITS
    ᾧ
    1.19
     envis
    1.17
    rne
    1.12
     लेट्स
    1.12
    ਆਂ
    1.09
    નાં
    1.05
     Corfu
    1.05
     quantized
    1.02
     intervals
    1.02
    rauch
    1.02
    Act Density 0.000%

    No Known Activations