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

    Neuronpedia

    INDEX
    Explanations

    Citations/Dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     amps
    -0.07
    UpInside
    -0.06
    (calendar
    -0.06
    .addTarget
    -0.06
    监听
    -0.06
     airspace
    -0.06
    าษฎ
    -0.06
    μάτων
    -0.06
    AndFeel
    -0.06
    intro
    -0.06
    POSITIVE LOGITS
     [--
    0.07
     Ratio
    0.07
    -plugins
    0.06
     Brittany
    0.06
     hlavou
    0.06
     humor
    0.06
    FromString
    0.06
     cautioned
    0.06
     victim
    0.06
    /event
    0.06
    Act Density 0.003%

    No Known Activations