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

    Neuronpedia

    INDEX
    Explanations

    legal citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🚖
    -0.08
    housing
    -0.08
    ᵌ
    -0.08
     cosmetics
    -0.07
     consumer
    -0.07
    ﲈ
    -0.07
    🕔
    -0.06
     vatandaş
    -0.06
    overview
    -0.06
    anced
    -0.06
    POSITIVE LOGITS
     Worksheet
    0.07
     grp
    0.07
     ArrayList
    0.07
    §
    0.07
    র
    0.07
    .getParent
    0.07
    ♖
    0.06
    _SR
    0.06
    щик
    0.06
     RK
    0.06
    Act Density 0.001%

    No Known Activations