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

    Neuronpedia

    INDEX
    Explanations

    Statement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rings
    -0.08
     Episodes
    -0.08
    _Frame
    -0.07
    خان
    -0.07
    nické
    -0.07
    ерб
    -0.06
     Nora
    -0.06
    azines
    -0.06
    GGLE
    -0.06
    --------↵↵
    -0.06
    POSITIVE LOGITS
     adec
    0.07
    液
    0.06
    @ResponseBody
    0.06
     uncertain
    0.06
     выход
    0.06
    _CONFIRM
    0.06
    .assertIsNot
    0.06
    藤
    0.06
     determin
    0.06
    Trying
    0.06
    Act Density 0.006%

    No Known Activations