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

    Neuronpedia

    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Faction
    -0.06
    人的
    -0.06
     todd
    -0.06
    -tags
    -0.06
     Murdoch
    -0.06
     下
    -0.06
     inauguration
    -0.06
    ulas
    -0.06
     martyr
    -0.06
    ++){↵
    -0.06
    POSITIVE LOGITS
     LZ
    0.07
    anno
    0.06
    =.
    0.06
     schon
    0.06
     surg
    0.06
     Erk
    0.06
    Unc
    0.06
    вана
    0.06
    -none
    0.06
    openid
    0.06
    Act Density 0.027%

    No Known Activations