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

    Neuronpedia

    INDEX
    Explanations

    Story excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     初始化
    -0.06
     світі
    -0.06
    ќ
    -0.06
     insights
    -0.06
    ků
    -0.06
    [var
    -0.06
    ικοί
    -0.06
     Aw
    -0.06
     Lon
    -0.06
     yere
    -0.06
    POSITIVE LOGITS
     kennenlernen
    0.07
     Buenos
    0.07
    道
    0.06
     Pathfinder
    0.06
     Penal
    0.06
     grieving
    0.06
    :N
    0.06
     Saskatchewan
    0.06
     NBC
    0.06
     كن
    0.06
    Act Density 0.051%

    No Known Activations