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

    Neuronpedia

    INDEX
    Explanations

    interface

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    88
    -0.07
     snow
    -0.07
     poll
    -0.06
     �
    -0.06
     Gol
    -0.06
    	pos
    -0.06
     retention
    -0.06
     Top
    -0.06
    拼
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     interface
    0.09
     Interface
    0.09
    Interface
    0.09
     interfaces
    0.08
     interf
    0.08
     Interfaces
    0.08
    -interface
    0.08
     Masc
    0.07
     diced
    0.07
    {EIF
    0.07
    Act Density 0.016%

    No Known Activations