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

    Neuronpedia

    INDEX
    Explanations

    November dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    وير
    0.45
     submits
    0.44
    zaXR
    0.44
     বর্ষ
    0.42
     महिन्यात
    0.42
     imasmim
    0.40
    <unused183>
    0.40
     auxqu
    0.40
    msgs
    0.39
    重建
    0.39
    POSITIVE LOGITS
    ari
    0.46
     lot
    0.45
    //
    0.44
     partic
    0.43
    ott
    0.43
    i
    0.43
    otten
    0.42
    s
    0.42
    et
    0.42
    x
    0.42
    Act Density 0.001%

    No Known Activations