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

    Neuronpedia

    INDEX
    Explanations

    notion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     encour
    -0.07
    �
    -0.07
    	random
    -0.07
    раль
    -0.07
     Trung
    -0.07
     todos
    -0.06
    	active
    -0.06
     mpg
    -0.06
     cig
    -0.06
    -alpha
    -0.06
    POSITIVE LOGITS
     notion
    0.10
     notions
    0.08
    .snapshot
    0.07
     Boulevard
    0.07
     bout
    0.07
    ilion
    0.07
     SOL
    0.06
     plot
    0.06
     vowed
    0.06
     thinking
    0.06
    Act Density 0.003%

    No Known Activations