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

    Neuronpedia

    INDEX
    Explanations

    suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Horn
    -0.07
     brand
    -0.07
     definitive
    -0.07
    Au
    -0.07
    anine
    -0.06
    ,msg
    -0.06
    Resp
    -0.06
    Checks
    -0.06
     quanto
    -0.06
     besoin
    -0.06
    POSITIVE LOGITS
     breadcrumbs
    0.07
     metaData
    0.06
    //**↵
    0.06
    	Server
    0.06
     Bình
    0.06
    ตาม
    0.06
     bzw
    0.06
    ге
    0.06
     marrow
    0.06
     ----------↵
    0.06
    Act Density 0.003%

    No Known Activations