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

    Neuronpedia

    INDEX
    Explanations

    virtual machine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    सोई
    0.56
     রহিল
    0.47
     encontraba
    0.44
    筫
    0.43
     называется
    0.43
    ▔
    0.43
     حقی
    0.42
    欴
    0.42
     senhor
    0.41
    0.41
    POSITIVE LOGITS
     creates
    0.44
     has
    0.43
     (
    0.43
     <
    0.41
    .,
    0.40
    (-
    0.39
     D
    0.38
     Podcast
    0.38
     *
    0.38
    \[
    0.38
    Act Density 0.001%

    No Known Activations