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

    Neuronpedia

    INDEX
    Explanations

    Device driver abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dog
    -0.08
    ZO
    -0.07
    Pixmap
    -0.07
     bulletin
    -0.07
     IDb
    -0.07
    navigator
    -0.06
     Katrina
    -0.06
     database
    -0.06
     PowerShell
    -0.06
     intents
    -0.06
    POSITIVE LOGITS
    於
    0.06
    inea
    0.06
    俄
    0.06
     usu
    0.06
    帰
    0.06
     giảm
    0.06
    ($('
    0.05
     birinci
    0.05
    WO
    0.05
    >'+
    0.05
    Act Density 0.010%

    No Known Activations