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

    Neuronpedia

    INDEX
    Explanations

    unce

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ContainsKey
    -0.07
    八
    -0.06
    ì
    -0.06
     wastewater
    -0.06
     incurred
    -0.06
     전국
    -0.06
    _CHANNELS
    -0.06
    addAction
    -0.06
     Germans
    -0.06
     Laguna
    -0.05
    POSITIVE LOGITS
    _TOPIC
    0.07
    рош
    0.07
    γή
    0.07
     viewController
    0.07
    форт
    0.07
    ро
    0.06
    Core
    0.06
    ,%
    0.06
     Candy
    0.06
     cây
    0.06
    Act Density 0.002%

    No Known Activations