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

    Neuronpedia

    INDEX
    Explanations

    asking for explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     podrás
    0.35
     היי
    0.30
     имен
    0.30
     SCHEMA
    0.29
     ஜ
    0.29
     ScriptInterface
    0.29
     아주
    0.28
     RST
    0.28
    _{*}\
    0.28
     OST
    0.28
    POSITIVE LOGITS
     why
    0.63
    why
    0.57
     mengapa
    0.53
    那么多
    0.52
    Why
    0.51
    這麼
    0.51
     so
    0.50
    如此
    0.50
    为什么
    0.48
     warum
    0.48
    Act Density 0.328%

    No Known Activations