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

    Neuronpedia

    INDEX
    Explanations

    code delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _neighbor
    -0.09
     neighbor
    -0.09
     colega
    -0.08
     equation
    -0.08
    Neighbor
    -0.07
     vecino
    -0.07
     inequality
    -0.07
    Equation
    -0.07
     distributor
    -0.07
     Equation
    -0.07
    POSITIVE LOGITS
     folders
    0.10
     sections
    0.09
     katalog
    0.09
     Collections
    0.09
     Organized
    0.09
     folder
    0.08
     каталог
    0.08
     ವಿಭಾಗ
    0.08
     Stories
    0.08
     বিভাগ
    0.08
    Act Density 0.010%

    No Known Activations