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

    Neuronpedia

    INDEX
    Explanations

    the, of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ăn
    -0.07
    Reading
    -0.07
    以人为
    -0.07
    �
    -0.07
     Cowboy
    -0.07
    ossa
    -0.06
    Lİ
    -0.06
     useDispatch
    -0.06
    ichage
    -0.06
    xz
    -0.06
    POSITIVE LOGITS
    层面
    0.08
    	echo
    0.07
    求
    0.07
    獎
    0.07
    不會
    0.07
    Factory
    0.07
    ateg
    0.07
     award
    0.07
    要求
    0.07
     disco
    0.07
    Act Density 0.016%

    No Known Activations