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

    Neuronpedia

    INDEX
    Explanations

    questions and choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ギフト
    0.48
     کا
    0.47
     perempt
    0.46
     ಅಥವಾ
    0.46
     genuine
    0.44
     دون
    0.44
     områ
    0.43
     شدن
    0.43
     Marche
    0.43
     കാരണ
    0.43
    POSITIVE LOGITS
    elenggarakan
    0.44
    აზე
    0.44
    ड़े
    0.43
    ىلى
    0.43
    installer
    0.41
    به
    0.40
     haszn
    0.40
    rl
    0.40
     \
    0.39
    安装
    0.39
    Act Density 0.264%

    No Known Activations