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

    Neuronpedia

    INDEX
    Explanations

    dialogue indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     começa
    1.21
    avourite
    1.15
     يا
    1.14
     thrives
    1.14
    ße
    1.12
    ación
    1.10
     yapar
    1.09
     tenho
    1.09
     messed
    1.09
     gets
    1.08
    POSITIVE LOGITS
     Lâm
    0.95
     Workers
    0.89
     ശക്ത
    0.88
    更多
    0.86
    主要
    0.84
    ："
    0.81
    㖮
    0.80
     বিষয়
    0.80
     notamment
    0.80
     Officials
    0.79
    Act Density 0.020%

    No Known Activations