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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disdain
    -0.07
    	text
    -0.07
    Rich
    -0.07
     has
    -0.07
     Libert
    -0.07
     Race
    -0.06
     scares
    -0.06
     Quinn
    -0.06
     Qty
    -0.06
     Alta
    -0.06
    POSITIVE LOGITS
    ρίζ
    0.06
    EditMode
    0.06
    ITHER
    0.06
    serializer
    0.06
    	component
    0.06
    .execute
    0.06
    consumer
    0.06
    .rotate
    0.06
    xfd
    0.06
    .integration
    0.06
    Act Density 0.011%

    No Known Activations