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

    Neuronpedia

    INDEX
    Explanations

    locations after 'in' or 'from'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    URA
    0.78
    roquois
    0.76
     બાળકો
    0.75
    ンスター
    0.74
    ዩ
    0.72
     高級
    0.71
    ̎
    0.71
    級
    0.70
    菓子
    0.70
    glio
    0.70
    POSITIVE LOGITS
     your
    0.83
    your
    0.77
    umbai
    0.74
     혹은
    0.73
     rằng
    0.71
     or
    0.71
     Ireland
    0.69
    或者是
    0.69
     किंवा
    0.68
    Cork
    0.67
    Act Density 0.001%

    No Known Activations