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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ngân
    -0.07
    (Function
    -0.06
     bunun
    -0.06
    ственная
    -0.06
     anus
    -0.06
     sentinel
    -0.06
    agree
    -0.06
     tái
    -0.06
    haps
    -0.06
     menší
    -0.06
    POSITIVE LOGITS
     dictionaryWith
    0.07
    stor
    0.07
    ава
    0.06
     foreclosure
    0.06
     disclosures
    0.06
     three
    0.06
     Score
    0.06
     four
    0.06
     روی
    0.06
     discredit
    0.06
    Act Density 0.000%

    No Known Activations