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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мор
    -0.06
     LUA
    -0.06
     nationality
    -0.06
     Surprise
    -0.06
     Numeric
    -0.06
     использу
    -0.06
     Việc
    -0.06
     democracy
    -0.06
     العرب
    -0.06
     broadcasters
    -0.06
    POSITIVE LOGITS
    [np
    0.07
    arhus
    0.07
    (gca
    0.07
     �
    0.07
    '):
↵
    0.07
    써
    0.06
     Pregnancy
    0.06
    '],
↵
    0.06
    าหล
    0.06
     imap
    0.06
    Act Density 0.016%

    No Known Activations