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

    Neuronpedia

    INDEX
    Explanations

    Title and headlines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bởi
    0.50
     γά
    0.47
     Dahmer
    0.43
    ﻚ
    0.42
     tuo
    0.41
     rapidamente
    0.41
    工作
    0.41
     importante
    0.41
     importantes
    0.41
    鏈
    0.41
    POSITIVE LOGITS
    äck
    0.49
    ров
    0.46
    aning
    0.46
    óst
    0.46
    char
    0.45
    یش
    0.45
     دارد
    0.44
     ശിഷ്യ
    0.43
     봐야
    0.43
     slump
    0.43
    Act Density 0.001%

    No Known Activations