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

    Neuronpedia

    INDEX
    Explanations

    multilingual sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     crux
    0.28
     hamstring
    0.26
     arugula
    0.25
     capitalizing
    0.25
     stronę
    0.25
     עם
    0.24
     connaissance
    0.24
     эмне
    0.24
     conclusão
    0.24
     ليس
    0.24
    POSITIVE LOGITS
    T
    0.30
    M
    0.30
    W
    0.30
    I
    0.28
    S
    0.26
    D
    0.26
    っている
    0.25
    {
    0.25
    \
    0.25
    B
    0.25
    Act Density 0.063%

    No Known Activations