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

    Neuronpedia

    INDEX
    Explanations

    referrals to services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ジ
    0.81
     আগের
    0.76
    ÁN
    0.75
     ア
    0.75
    ジェット
    0.75
    ﻄ
    0.72
     ছুটিতে
    0.72
     nCmd
    0.72
     pane
    0.71
     下さい
    0.71
    POSITIVE LOGITS
     till
    2.16
     til
    1.87
     until
    1.71
     đến
    1.69
     Till
    1.58
     до
    1.58
    Till
    1.54
    till
    1.54
    到
    1.54
     toward
    1.51
    Act Density 0.020%

    No Known Activations