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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rangers
    -0.07
     Mutable
    -0.06
    	offset
    -0.06
     Bobby
    -0.06
     sacrifices
    -0.06
    šetř
    -0.06
     polygon
    -0.06
    “As
    -0.06
     prerequisites
    -0.06
     athletic
    -0.06
    POSITIVE LOGITS
    ्डल
    0.06
    (delete
    0.06
    iators
    0.06
    -authored
    0.06
    .parser
    0.06
    ников
    0.06
    冊
    0.06
    one
    0.06
    ий
    0.06
    )])↵↵
    0.06
    Act Density 0.031%

    No Known Activations