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

    Neuronpedia

    INDEX
    Explanations

    City names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CHASE
    -0.07
    وئ
    -0.06
    YRO
    -0.06
     Sundays
    -0.06
    benchmark
    -0.06
    MISSION
    -0.06
     вероят
    -0.06
     결정
    -0.06
     patented
    -0.06
    ім
    -0.06
    POSITIVE LOGITS
    χος
    0.07
    .@
    0.07
    .standard
    0.07
    .WEST
    0.07
    yps
    0.06
    _word
    0.06
    .Field
    0.06
    _ci
    0.06
     ….
    0.06
     星
    0.06
    Act Density 0.105%

    No Known Activations