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

    Neuronpedia

    INDEX
    Explanations

    actions and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     or
    0.31
    と思いますが
    0.30
     किंवा
    0.30
     your
    0.29
     means
    0.29
    하거나
    0.29
     podemos
    0.29
     நீங்கள்
    0.29
     work
    0.28
     helps
    0.28
    POSITIVE LOGITS
    。
    0.40
    .
    0.31
    ։
    0.31
    ។
    0.28
    ској
    0.28
    。「
    0.28
     furiously
    0.28
    ।
    0.27
    ．
    0.27
    .“
    0.27
    Act Density 0.260%

    No Known Activations