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

    Neuronpedia

    INDEX
    Explanations

    VPN configuration files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kum
    0.40
     truncation
    0.39
     થયું
    0.39
    Fifty
    0.39
     الزد
    0.38
    大手
    0.38
     खरा
    0.38
    rangea
    0.37
    ۲۰
    0.36
    akum
    0.36
    POSITIVE LOGITS
    jars
    0.41
     Push
    0.39
    8
    0.39
     Пере
    0.38
    เยี่ยม
    0.37
     Monday
    0.37
    学习
    0.35
     orth
    0.34
     WLAN
    0.34
     Pers
    0.34
    Act Density 0.005%

    No Known Activations