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

    Neuronpedia

    INDEX
    Explanations

    figures in technical diagrams

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    issuer
    -0.07
    Ⓛ
    -0.07
     가지고
    -0.07
    保密
    -0.07
    沄
    -0.07
     peers
    -0.07
     lashes
    -0.07
    -Za
    -0.07
     affluent
    -0.06
     الخي
    -0.06
    POSITIVE LOGITS
     пример
    0.08
    Num
    0.08
     simpler
    0.07
    类似的
    0.07
     Sort
    0.07
    進め
    0.07
    _REC
    0.07
     ///↵
    0.07
     infrastructure
    0.07
     happier
    0.07
    Act Density 0.028%

    No Known Activations