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

    Neuronpedia

    INDEX
    Explanations

    places and interfaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     svoju
    0.23
     ぐらい
    0.23
     являются
    0.22
     تربيع
    0.22
    过来
    0.22
     semicolon
    0.22
    வரின்
    0.22
    不是
    0.21
     imaju
    0.21
     проек
    0.21
    POSITIVE LOGITS
    allowing
    0.33
     allowing
    0.29
    containing
    0.27
    /
    0.26
     for
    0.25
    allow
    0.25
    For
    0.24
    ucked
    0.24
    Entry
    0.23
     containing
    0.23
    Act Density 0.480%

    No Known Activations