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

    Neuronpedia

    INDEX
    Explanations

    Obama

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IFA
    -0.07
    質
    -0.07
    组
    -0.07
     generated
    -0.06
     optimized
    -0.06
    ynos
    -0.06
    anguage
    -0.06
     UT
    -0.06
    rale
    -0.06
     for
    -0.06
    POSITIVE LOGITS
    (typeof
    0.07
    [SerializeField
    0.07
     худ
    0.06
     мої
    0.06
    ("${
    0.06
    Comic
    0.06
     Archived
    0.06
    arth
    0.06
    \controllers
    0.06
    +)\
    0.06
    Act Density 0.073%

    No Known Activations