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

    Neuronpedia

    INDEX
    Explanations

    Incomplete sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     универ
    -0.07
    "At
    -0.07
     bright
    -0.07
     companies
    -0.07
     Electoral
    -0.06
    go
    -0.06
     Bare
    -0.06
     Bry
    -0.06
    ye
    -0.06
     Dy
    -0.06
    POSITIVE LOGITS
    вают
    0.07
    ------------------------------
    0.07
     ]}↵
    0.07
    **/↵
    0.06
    вався
    0.06
    )}
↵
    0.06
    니다
    0.06
     Hogwarts
    0.06
    postId
    0.06
    "/>.↵
    0.06
    Act Density 0.006%

    No Known Activations