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

    Neuronpedia

    INDEX
    Explanations

    chapter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sex
    -0.06
    mue
    -0.06
    oids
    -0.06
    dens
    -0.06
     ση
    -0.06
    .FLOAT
    -0.06
     عص
    -0.06
    <translation
    -0.06
    selectors
    -0.06
    성이
    -0.06
    POSITIVE LOGITS
     Chapter
    0.12
     chapter
    0.11
    chapter
    0.11
    Chapter
    0.10
     Harper
    0.09
     chapters
    0.08
    	category
    0.08
    Page
    0.08
    _when
    0.08
     chap
    0.08
    Act Density 0.009%

    No Known Activations