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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quarters
    -0.07
     NRA
    -0.07
    increments
    -0.06
    channels
    -0.06
    isspace
    -0.06
    	List
    -0.06
    irts
    -0.06
     ।
    -0.06
     Luxury
    -0.06
     scratch
    -0.06
    POSITIVE LOGITS
    oriasis
    0.07
    .ToolTip
    0.07
    /csv
    0.06
     qed
    0.06
    -prev
    0.06
    Throwable
    0.05
    -exclusive
    0.05
    ColumnInfo
    0.05
    든
    0.05
    pellier
    0.05
    Act Density 0.024%

    No Known Activations