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

    Neuronpedia

    INDEX
    Explanations

    Paper,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iface
    -0.09
     fullness
    -0.09
    bye
    -0.08
     चीज
    -0.08
    nten
    -0.08
    atom
    -0.08
    entity
    -0.07
    tainment
    -0.07
     dissolution
    -0.07
    lock
    -0.07
    POSITIVE LOGITS
     pamph
    0.11
     brochures
    0.09
     brochure
    0.09
     unpublished
    0.09
     Publications
    0.08
     bulletin
    0.08
     symposium
    0.08
    发表于
    0.08
     ಪತ್ರ
    0.08
     Bulletin
    0.08
    Act Density 0.035%

    No Known Activations