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

    Neuronpedia

    INDEX
    Explanations

    uniqueness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ustr
    -0.07
    �
    -0.07
    ("")↵
    -0.07
    357
    -0.06
    cích
    -0.06
    getPath
    -0.06
     ""↵↵
    -0.06
    riad
    -0.06
    inerary
    -0.06
    ""
    -0.06
    POSITIVE LOGITS
    읍
    0.07
     feeding
    0.07
     правда
    0.07
     contempor
    0.06
     предпри
    0.06
     يت
    0.06
     vocalist
    0.06
     aydın
    0.06
     (::
    0.06
     velk
    0.06
    Act Density 0.097%

    No Known Activations