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

    Neuronpedia

    INDEX
    Explanations

    driving license

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     claust
    1.07
     landfall
    1.06
     divertido
    1.06
    roomId
    1.05
    下载
    1.05
     shi
    1.02
     pidió
    1.01
     pensado
    0.99
    iax
    0.98
     Bóng
    0.97
    POSITIVE LOGITS
    ли
    0.86
    સમ
    0.84
    пов
    0.81
    ला
    0.80
     Dile
    0.78
     Func
    0.78
    ри
    0.74
    princip
    0.73
    Hood
    0.73
     Discourse
    0.72
    Act Density 0.013%

    No Known Activations