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

    Neuronpedia

    INDEX
    Explanations

    both sets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    al
    0.59
    alim
    0.47
     ndị
    0.45
    듑
    0.44
    ర్థిక
    0.44
     watu
    0.43
     ahli
    0.42
    მდეგ
    0.42
    ‌,
    0.42
    ambarkan
    0.41
    POSITIVE LOGITS
    NE
    0.57
    ك
    0.54
    沱
    0.52
    Año
    0.50
    वल
    0.50
     terrestre
    0.49
    اسة
    0.48
    み
    0.47
     that
    0.47
    ès
    0.47
    Act Density 0.005%

    No Known Activations