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

    Neuronpedia

    INDEX
    Explanations

    quotations/brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sharing
    -0.07
     breve
    -0.06
    fig
    -0.06
     gå
    -0.06
     MIS
    -0.06
    ITTER
    -0.06
    quoted
    -0.06
    GPS
    -0.06
    Amazon
    -0.06
     Imaging
    -0.06
    POSITIVE LOGITS
    owell
    0.07
     особлив
    0.07
    ază
    0.06
    .white
    0.06
     consequently
    0.06
    čen
    0.06
     session
    0.06
    全
    0.06
    .categories
    0.06
    В
    0.06
    Act Density 0.027%

    No Known Activations