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

    Neuronpedia

    INDEX
    Explanations

    list structure markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     הפ
    0.46
     επέ
    0.46
    istence
    0.46
     Toen
    0.46
    验证
    0.45
    导致
    0.44
     chuva
    0.43
    变得
    0.43
    κα
    0.42
    Пе
    0.42
    POSITIVE LOGITS
     inflamm
    0.54
     lyn
    0.50
     nikk
    0.46
     novas
    0.46
    arlar
    0.45
     gneiss
    0.45
    ︰
    0.45
    〞
    0.45
     polls
    0.44
     konus
    0.44
    Act Density 0.002%

    No Known Activations