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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bölges
    -0.07
    Multiplicity
    -0.07
    的一个
    -0.07
     stole
    -0.07
    분
    -0.07
     crore
    -0.06
    认购
    -0.06
     pursuing
    -0.06
    getNode
    -0.06
     multiples
    -0.06
    POSITIVE LOGITS
     TASK
    0.07
     concerts
    0.07
    ,l
    0.06
    给力
    0.06
     BREAK
    0.06
     }
↵
↵
    0.06
    Work
    0.06
     produk
    0.06
    ])
↵
↵
    0.06
    +p
    0.06
    Act Density 0.002%

    No Known Activations