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

    Neuronpedia

    INDEX
    Explanations

    idea originates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Д
    0.47
    ма
    0.45
    Harvard
    0.43
     нагрузки
    0.43
    <unused0>
    0.43
    </h2>
    0.43
    actus
    0.42
     malfunction
    0.42
     акты
    0.42
     Whitehall
    0.42
    POSITIVE LOGITS
     zuk
    0.45
    潺
    0.43
     latt
    0.41
    シン
    0.40
     équipé
    0.40
     hei
    0.40
     trae
    0.39
    <0x8F>
    0.39
     دوسرے
    0.39
     ينا
    0.39
    Act Density 0.006%

    No Known Activations