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

    Neuronpedia

    INDEX
    Explanations

    //

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    匏
    -0.08
     Asphalt
    -0.07
     męsk
    -0.07
    装
    -0.07
     Army
    -0.07
     communism
    -0.07
     Video
    -0.07
     Zeus
    -0.07
    道教
    -0.07
    ankind
    -0.07
    POSITIVE LOGITS
    Serializer
    0.08
    _RULE
    0.07
    _threads
    0.07
     eer
    0.07
     boiler
    0.07
    Albert
    0.06
    例
    0.06
     vale
    0.06
     SOURCE
    0.06
    	source
    0.06
    Act Density 0.005%

    No Known Activations