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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     번
    -0.07
    θο
    -0.07
    か
    -0.06
    isted
    -0.06
    Codigo
    -0.06
    Eq
    -0.06
     respect
    -0.06
    tracts
    -0.06
    Ticks
    -0.06
    잖
    -0.06
    POSITIVE LOGITS
    .fre
    0.07
     Compass
    0.06
    ylül
    0.06
     těž
    0.06
     configurable
    0.06
     Intervention
    0.06
     qry
    0.06
    996
    0.06
    ्च
    0.06
     newList
    0.06
    Act Density 0.002%

    No Known Activations