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

    Neuronpedia

    INDEX
    Explanations

    page or slide 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ли
    0.65
     elastic
    0.50
     fá
    0.48
    hotel
    0.47
    ung
    0.46
     memória
    0.46
     zá
    0.46
     moisturizing
    0.46
     decon
    0.46
    غ
    0.46
    POSITIVE LOGITS
    چی
    0.47
     ITEMIZED
    0.46
     MDLVertex
    0.45
     குறித்து
    0.45
        
    0.43
    vić
    0.42
     निर्मा
    0.42
    ຂອງ
    0.41
     Continuing
    0.41
    )')
    0.41
    Act Density 0.023%

    No Known Activations