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

    Neuronpedia

    INDEX
    Explanations

    seeds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _BATCH
    -0.07
    睥
    -0.07
     paylaş
    -0.07
    _Button
    -0.07
     lat
    -0.06
    发扬
    -0.06
     �
    -0.06
    썬
    -0.06
     convenient
    -0.06
    _drawer
    -0.06
    POSITIVE LOGITS
    xito
    0.07
    为
    0.07
    Ĺ
    0.07
    	results
    0.07
     środow
    0.07
    �
    0.07
    对其进行
    0.06
    test
    0.06
     tests
    0.06
     Conexion
    0.06
    Act Density 0.005%

    No Known Activations