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

    Neuronpedia

    INDEX
    Explanations

    URLs containing ://

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    સ
    2.20
    ка
    2.12
    2.07
    ла
    2.07
    స్‌
    2.06
    ru
    2.01
     ambayo
    2.01
    р
    2.00
     পাগল
    1.99
    da
    1.98
    POSITIVE LOGITS
    ه
    2.80
    ン
    2.58
     dàng
    2.42
    ம்
    2.35
    ाना
    2.25
    ς
    2.24
    𝗽
    2.19
    가
    2.18
    ة
    2.18
     marketed
    2.13
    Act Density 0.210%

    No Known Activations