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

    Neuronpedia

    INDEX
    Explanations

    do

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aso
    -0.08
    Coefficient
    -0.08
    Notation
    -0.07
     усили
    -0.07
     quasi
    -0.07
     Ethics
    -0.07
     conformité
    -0.07
    _constants
    -0.07
     शक्त
    -0.07
    .power
    -0.07
    POSITIVE LOGITS
     entertainment
    0.10
    体验
    0.09
     loisirs
    0.09
    娱乐
    0.09
     aktiviteter
    0.09
     indoors
    0.09
     sightseeing
    0.09
     wisata
    0.09
     offerings
    0.09
     options
    0.09
    Act Density 0.037%

    No Known Activations