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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jackets
    -0.07
    δόν
    -0.07
    urnished
    -0.07
     Supply
    -0.06
     vier
    -0.06
     Least
    -0.06
     TextView
    -0.06
    イト
    -0.06
    /mod
    -0.06
    γραφ
    -0.06
    POSITIVE LOGITS
     soát
    0.07
    :eq
    0.06
    .pb
    0.06
    ỹ
    0.06
    esity
    0.06
     _$
    0.06
     Yas
    0.06
     따른
    0.06
    .UN
    0.06
    _DE
    0.06
    Act Density 0.027%

    No Known Activations