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

    Neuronpedia

    INDEX
    Explanations

    targeted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     سازی
    -0.07
     월세
    -0.07
    irket
    -0.06
    etrain
    -0.06
     raging
    -0.06
    bitset
    -0.06
    .session
    -0.06
    /pro
    -0.06
    Random
    -0.06
     caches
    -0.06
    POSITIVE LOGITS
     birden
    0.06
     inference
    0.06
    ingu
    0.06
    (Integer
    0.06
     призначення
    0.06
     Temmuz
    0.06
     situación
    0.06
     infant
    0.06
    _detection
    0.06
    _analysis
    0.06
    Act Density 0.003%

    No Known Activations