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
    átis
    -0.07
     })).
    -0.07
     pearl
    -0.06
     먼저
    -0.06
    iosis
    -0.06
     cere
    -0.06
    _Pl
    -0.06
     competitiveness
    -0.06
     hãng
    -0.06
    naires
    -0.06
    POSITIVE LOGITS
    Filename
    0.07
     Scho
    0.06
     FIFO
    0.06
    AL
    0.06
     Twitter
    0.06
    REPORT
    0.06
    訳
    0.06
    =back
    0.06
     cic
    0.06
    =my
    0.06
    Act Density 0.002%

    No Known Activations