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

    Neuronpedia

    INDEX
    Explanations

    alternating turns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dang
    1.24
    ranton
    1.20
    ी
    1.18
    हिणी
    1.09
     környez
    1.05
    kjhtml
    1.04
     UInt
    1.03
    เลือด
    1.03
    രി
    1.03
     toric
    1.02
    POSITIVE LOGITS
    ik
    1.32
    िष्ट
    1.22
    র্য
    1.16
    sigh
    1.15
    आ
    1.13
    ﺭ
    1.12
     яка
    1.11
    Swap
    1.10
     Особенно
    1.09
    ತ
    1.09
    Act Density 0.051%

    No Known Activations