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

    Neuronpedia

    INDEX
    Explanations

    Greater

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    人民银行
    -0.07
    -rock
    -0.07
     Trav
    -0.07
    Proc
    -0.07
    slaught
    -0.07
    טים
    -0.06
     runs
    -0.06
    ensburg
    -0.06
    igrated
    -0.06
     Tavern
    -0.06
    POSITIVE LOGITS
     african
    0.07
     approximately
    0.07
    yx
    0.07
     branch
    0.07
    的标准
    0.07
     reducer
    0.07
     lowered
    0.07
    합니다
    0.06
    一侧
    0.06
    Relation
    0.06
    Act Density 0.003%

    No Known Activations