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

    Neuronpedia

    INDEX
    Explanations

    software models and search queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bach
    -0.89
     Sinon
    -0.81
     افزایش
    -0.77
     gratuitas
    -0.75
    Комплек
    -0.73
     Praga
    -0.73
     Darm
    -0.72
    ˅
    -0.72
     Ferdin
    -0.72
     réuss
    -0.71
    POSITIVE LOGITS
     Search
    0.92
     search
    0.83
     Rep
    0.83
     particularmente
    0.82
    search
    0.82
    yt
    0.81
     Walmart
    0.81
    EXTERN
    0.78
    Search
    0.77
     Castillo
    0.77
    Act Density 0.011%

    No Known Activations