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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ‌ده
    -0.08
    桌
    -0.08
     chemistry
    -0.08
     поверхности
    -0.08
     Hid
    -0.08
     pagk
    -0.07
     üzerinde
    -0.07
     Landes
    -0.07
     respons
    -0.07
    LY
    -0.07
    POSITIVE LOGITS
    进去
    0.15
    _into
    0.14
    Into
    0.14
    into
    0.13
     넣
    0.13
     vào
    0.13
     into
    0.12
    入
    0.12
     प्रवेश
    0.12
     hinein
    0.12
    Act Density 0.072%

    No Known Activations