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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     зад
    -0.07
    properties
    -0.07
     Carol
    -0.07
     convin
    -0.06
     parsers
    -0.06
     yaz
    -0.06
    lerini
    -0.06
    ष
    -0.06
    incer
    -0.06
    	old
    -0.06
    POSITIVE LOGITS
     deutsch
    0.07
    =$((
    0.07
     šest
    0.07
    ,min
    0.07
     RR
    0.06
    ddl
    0.06
     berry
    0.06
     ([[
    0.06
    MySQL
    0.06
    .test
    0.06
    Act Density 0.038%

    No Known Activations