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

    Neuronpedia

    INDEX
    Explanations

    codec

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    नेस
    -0.08
     crime
    -0.08
    णे
    -0.07
     Rae
    -0.07
     stakeholder
    -0.07
     bekomme
    -0.07
     Garage
    -0.07
     corporate
    -0.07
     Individuals
    -0.07
     Bliss
    -0.07
    POSITIVE LOGITS
    _initialized
    0.10
    .init
    0.08
    왕
    0.08
     által
    0.08
     mism
    0.08
     الشمس
    0.08
    (cols
    0.08
    matched
    0.08
     cols
    0.08
     wedstrijden
    0.08
    Act Density 0.002%

    No Known Activations