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

    Neuronpedia

    INDEX
    Explanations

    Table

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verwerking
    -0.08
     verarbeitet
    -0.08
    ichern
    -0.08
    Subset
    -0.08
     yöntem
    -0.08
    Silent
    -0.08
    Verification
    -0.08
    			 ↵
    -0.08
    Density
    -0.08
    ffen
    -0.07
    POSITIVE LOGITS
    目录
    0.10
     syllabus
    0.10
     contents
    0.10
     Contents
    0.09
    yllabus
    0.09
     headings
    0.09
     capítulos
    0.08
     Inhalts
    0.08
     matières
    0.08
     splitter
    0.08
    Act Density 0.006%

    No Known Activations