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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ested
    -0.07
     Kg
    -0.07
     VI
    -0.07
    ))↵
    -0.07
     Workers
    -0.06
    Interestingly
    -0.06
    omas
    -0.06
    Translation
    -0.06
    vy
    -0.06
     Dense
    -0.06
    POSITIVE LOGITS
     iddi
    0.07
     příprav
    0.07
     phim
    0.06
     극
    0.06
     السعود
    0.06
     yeri
    0.06
     اینترنتی
    0.06
     ближ
    0.06
     Mahm
    0.06
     Aralık
    0.06
    Act Density 0.067%

    No Known Activations