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

    Neuronpedia

    INDEX
    Explanations

    autonomous driving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    起動
    0.46
    роме
    0.43
     mane
    0.42
    厛
    0.40
    اهرين
    0.40
    龍
    0.40
    못
    0.40
    廟
    0.40
    貶
    0.40
     playthrough
    0.39
    POSITIVE LOGITS
    의
    0.57
    štění
    0.52
     ﺍﻟ
    0.52
    の
    0.50
    ко
    0.50
    น่า
    0.49
    ان
    0.48
    looms
    0.46
    ु
    0.45
    Fiscal
    0.45
    Act Density 0.001%

    No Known Activations