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

    Neuronpedia

    INDEX
    Explanations

    scientific research data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sutton
    -0.06
    Titan
    -0.06
     있어서
    -0.06
    Monkey
    -0.06
    Premium
    -0.06
    GetInstance
    -0.06
     المعلومات
    -0.05
    parer
    -0.05
    itez
    -0.05
    sampling
    -0.05
    POSITIVE LOGITS
    ेक
    0.07
    gm
    0.07
     Dropdown
    0.07
    acích
    0.07
    .at
    0.07
    _Input
    0.06
     esk
    0.06
     enjoying
    0.06
     bölg
    0.06
     مايو
    0.06
    Act Density 0.049%

    No Known Activations