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

    Neuronpedia

    INDEX
    Explanations

    key followed by to or is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ные
    0.57
    لنا
    0.55
    ל
    0.55
    лу
    0.54
    кну
    0.54
    кру
    0.54
    Declared
    0.54
    x
    0.54
    始めた
    0.53
    ятся
    0.53
    POSITIVE LOGITS
     to
    0.62
    。
    0.59
    amphetamine
    0.57
     eller
    0.57
    }}
    0.55
     alebo
    0.52
    AN
    0.51
     ശ്രദ്ധ
    0.51
     nebo
    0.50
     Headphones
    0.50
    Act Density 0.004%

    No Known Activations