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

    Neuronpedia

    INDEX
    Explanations

    project

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mapper
    -0.07
     fantast
    -0.07
    .getColor
    -0.07
     האי
    -0.07
    .imwrite
    -0.07
     lavish
    -0.07
     אינו
    -0.07
    墉
    -0.07
     באו
    -0.07
    .randn
    -0.06
    POSITIVE LOGITS
    ole
    0.08
    monster
    0.07
    Ads
    0.07
    칠
    0.07
    ws
    0.07
    চ
    0.07
     interés
    0.07
     stakes
    0.07
    机械
    0.06
    ites
    0.06
    Act Density 0.001%

    No Known Activations