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

    Neuronpedia

    INDEX
    Explanations

    technical specifications/types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     등의
    0.40
    Ｃ
    0.38
     Thiết
    0.38
     乀
    0.38
    鹧
    0.37
    ^{-\
    0.37
     Chips
    0.36
    Chips
    0.36
    icuous
    0.36
     十分
    0.36
    POSITIVE LOGITS
    ul
    0.43
     territory
    0.38
    ون
    0.36
     имя
    0.35
    ين
    0.35
     credentials
    0.34
     name
    0.34
     swoją
    0.33
    {
    0.33
     aliases
    0.32
    Act Density 0.011%

    No Known Activations