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

    Neuronpedia

    INDEX
    Explanations

    say [months of the year]

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    discard
    -0.08
    符合
    -0.06
    Primary
    -0.06
     �
    -0.06
    	suite
    -0.06
     �
    -0.06
    Aqu
    -0.06
    Charles
    -0.06
    Convertible
    -0.06
    兄
    -0.06
    POSITIVE LOGITS
    oài
    0.07
    ولا
    0.07
     구글
    0.07
    wie
    0.07
    DRAM
    0.07
     Then
    0.06
     ox
    0.06
     RETURN
    0.06
    ])]↵
    0.06
     bols
    0.06
    Act Density 0.019%

    No Known Activations