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

    Neuronpedia

    INDEX
    Explanations

    structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RGB
    -0.07
     TH
    -0.07
    noteq
    -0.07
     looping
    -0.06
    .used
    -0.06
     "{\"
    -0.06
    	txt
    -0.06
    ewish
    -0.06
    ots
    -0.06
    LAG
    -0.06
    POSITIVE LOGITS
     resulting
    0.06
    iversite
    0.06
     tec
    0.06
     среди
    0.06
     demos
    0.06
     relying
    0.06
     사항
    0.06
     *(*
    0.06
     combining
    0.06
     expos
    0.06
    Act Density 0.011%

    No Known Activations