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

    Neuronpedia

    INDEX
    Explanations

    **

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nepr
    -0.08
     importantly
    -0.08
     doc
    -0.07
     carp
    -0.07
    _doc
    -0.07
    民主
    -0.07
    /controller
    -0.07
     бес
    -0.07
     docs
    -0.07
    ého
    -0.07
    POSITIVE LOGITS
     Hierbij
    0.08
     जिसमें
    0.08
     Embassy
    0.08
     જેમાં
    0.08
     основу
    0.08
     zusammeng
    0.08
     rollen
    0.07
     aún
    0.07
    .vip
    0.07
     aun
    0.07
    Act Density 0.034%

    No Known Activations