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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Price
    -0.08
    дрес
    -0.07
     �
    -0.07
     ']
    -0.07
    shapes
    -0.07
    �
    -0.06
     ez
    -0.06
    gp
    -0.06
    prites
    -0.06
    .gr
    -0.06
    POSITIVE LOGITS
     enlarge
    0.07
     deliberate
    0.06
     commenting
    0.06
    찰
    0.06
    看看
    0.06
     président
    0.06
    Dict
    0.06
    -range
    0.06
     rented
    0.06
    �
    0.06
    Act Density 0.014%

    No Known Activations