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

    Neuronpedia

    INDEX
    Explanations

    HTML

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    %D
    -0.07
     Damon
    -0.07
    撰
    -0.07
     gdyż
    -0.07
    .generator
    -0.07
     sor
    -0.07
    髯
    -0.07
     sought
    -0.06
    .const
    -0.06
    瀼
    -0.06
    POSITIVE LOGITS
    ateway
    0.07
    save
    0.07
     Residential
    0.07
    	Size
    0.07
     PC
    0.07
     Anti
    0.07
    entence
    0.06
    tering
    0.06
    	Close
    0.06
     Prel
    0.06
    Act Density 0.007%

    No Known Activations