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

    Neuronpedia

    INDEX
    Explanations

    categories and classifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    颜
    -0.07
    .more
    -0.07
    .dictionary
    -0.07
     ให
    -0.07
    .Go
    -0.07
     tasted
    -0.07
     accomplishment
    -0.06
    lock
    -0.06
     observers
    -0.06
    的话
    -0.06
    POSITIVE LOGITS
    leveland
    0.06
    onomous
    0.06
     annotated
    0.06
    rito
    0.06
    евые
    0.06
     zmq
    0.06
     آن
    0.06
    ücken
    0.06
     getEmail
    0.06
    hevik
    0.06
    Act Density 0.133%

    No Known Activations