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

    Neuronpedia

    INDEX
    Explanations

    to from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     정보
    -0.07
     Haupt
    -0.07
     CircularProgressIndicator
    -0.06
     yaptık
    -0.06
     普
    -0.06
     документа
    -0.06
    _PROTOCOL
    -0.06
    Stra
    -0.06
    ادات
    -0.06
     specialization
    -0.06
    POSITIVE LOGITS
     resembl
    0.07
    　　　　　　　　　　　　　　　　
    0.06
    Alchemy
    0.06
    sg
    0.06
     BBQ
    0.06
    iscrimination
    0.06
    requirements
    0.06
    /mac
    0.06
     inbound
    0.06
    ri
    0.06
    Act Density 0.010%

    No Known Activations