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

    Neuronpedia

    INDEX
    Explanations

    pronouns and their actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.17
    ↵↵
    0.15
    يا
    0.14
     বলল
    0.14
    पा
    0.14
    า
    0.14
    ал
    0.14
    िस
    0.13
    قي
    0.13
     เชื่อ
    0.13
    POSITIVE LOGITS
     essentially
    0.17
     certainly
    0.17
     typically
    0.17
     sort
    0.15
     operate
    0.15
     often
    0.14
    pherds
    0.14
     themselves
    0.14
    eding
    0.14
     generally
    0.14
    Act Density 0.099%

    No Known Activations