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

    Neuronpedia

    INDEX
    Explanations

    Order

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    禮
    -0.07
    已被
    -0.07
    Mi
    -0.07
     EventEmitter
    -0.07
    �
    -0.07
    會
    -0.07
    找工作
    -0.07
    崶
    -0.06
    terr
    -0.06
    offer
    -0.06
    POSITIVE LOGITS
    dated
    0.07
    等一批
    0.07
     Aberdeen
    0.07
     Globe
    0.07
    歼
    0.07
    -tra
    0.07
    ippet
    0.06
    淘汰
    0.06
     关
    0.06
    וץ
    0.06
    Act Density 0.047%

    No Known Activations