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

    Neuronpedia

    INDEX
    Explanations

    no extra cost or fault

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     verte
    0.39
    也不是
    0.39
     earthqu
    0.37
     hän
    0.37
    }<\
    0.36
     he
    0.36
     sele
    0.36
     pover
    0.36
     pomiesz
    0.36
     conduire
    0.36
    POSITIVE LOGITS
     вам
    0.46
    คุณ
    0.44
     உங்களுக்கு
    0.42
     дополни
    0.41
     ඔබට
    0.39
     Exchequer
    0.39
    ﻠ
    0.39
    их
    0.38
    artifact
    0.38
    你
    0.38
    Act Density 0.001%

    No Known Activations