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

    Neuronpedia

    INDEX
    Explanations

    transmitted, predict, Maria, butene

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     natomiast
    0.55
     ejecut
    0.54
     он
    0.52
     qí
    0.50
    肦
    0.50
    anı
    0.50
     ні
    0.49
     cakkh
    0.48
    mounted
    0.47
     inoltre
    0.47
    POSITIVE LOGITS
    بر
    0.49
    با
    0.49
     Walmart
    0.47
    زی
    0.46
    ความ
    0.45
    بار
    0.45
    نا
    0.44
    3
    0.44
    ما
    0.44
    Walmart
    0.44
    Act Density 0.002%

    No Known Activations