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

    Neuronpedia

    INDEX
    Explanations

    about waiting, lack, choice, sense

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    킵
    0.32
    mgr
    0.31
    zględ
    0.31
     fudai
    0.31
    steil
    0.31
     vuelos
    0.31
    ओसी
    0.30
     zvlá
    0.30
     ఇతర
    0.30
    snd
    0.30
    POSITIVE LOGITS
    ؔ
    0.36
    뭐
    0.36
    !
    0.35
    什麼
    0.34
    อะไร
    0.34
     something
    0.34
    什么
    0.33
     Constitu
    0.32
     нәрсә
    0.32
     gì
    0.31
    Act Density 0.189%

    No Known Activations