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

    Neuronpedia

    INDEX
    Explanations

    definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wo
    -0.06
    �
    -0.06
    _im
    -0.06
    paralle
    -0.06
    	go
    -0.06
    ()"↵
    -0.06
     onLoad
    -0.06
    剩
    -0.06
    “(
    -0.06
    Std
    -0.06
    POSITIVE LOGITS
     Receiver
    0.06
    TE
    0.06
     groupe
    0.06
    okin
    0.06
     definite
    0.06
     tum
    0.06
     deputies
    0.06
    ~~~~~~~~~~~~~~~~
    0.06
    sealed
    0.06
     JL
    0.06
    Act Density 0.033%

    No Known Activations