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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ानक
    -0.07
    バス
    -0.07
    рат
    -0.07
     seç
    -0.07
     Licht
    -0.07
     genera
    -0.06
     Literal
    -0.06
     putt
    -0.06
    クラブ
    -0.06
    bus
    -0.06
    POSITIVE LOGITS
    discover
    0.06
    Michigan
    0.06
    945
    0.06
    CppMethodPointer
    0.06
     blush
    0.06
    	public
    0.05
     Beginners
    0.05
     Barg
    0.05
    Mike
    0.05
     Gson
    0.05
    Act Density 0.002%

    No Known Activations