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

    Neuronpedia

    INDEX
    Explanations

    ->

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PLACE
    -0.07
    垸
    -0.07
    Ꭵ
    -0.06
    쫄
    -0.06
    솔
    -0.06
     נדר
    -0.06
    何种
    -0.06
    .is
    -0.06
    ን
    -0.06
    墓
    -0.06
    POSITIVE LOGITS
    imiters
    0.07
     Ergebn
    0.07
    奔驰
    0.07
    .smart
    0.07
     dever
    0.07
    用户体验
    0.07
     سوريا
    0.07
    /maps
    0.07
     Bringing
    0.07
     Showcase
    0.07
    Act Density 0.004%

    No Known Activations