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

    Neuronpedia

    INDEX
    Explanations

    atic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Oregon
    -0.08
    begin
    -0.08
    现实生活
    -0.08
    Allen
    -0.07
     Oregon
    -0.07
    -web
    -0.07
    Web
    -0.07
    oll
    -0.07
    EU
    -0.07
    献血
    -0.07
    POSITIVE LOGITS
    쨉
    0.07
     difíc
    0.07
     Damn
    0.07
    entlich
    0.07
    aat
    0.06
    atic
    0.06
    etxt
    0.06
    なぜ
    0.06
    溵
    0.06
    妈
    0.06
    Act Density 0.014%

    No Known Activations