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

    Neuronpedia

    INDEX
    Explanations

    interfering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Francisco
    -0.07
    ete
    -0.07
     marriage
    -0.06
    MSG
    -0.06
    memcmp
    -0.06
    rss
    -0.06
     cartel
    -0.06
     Doming
    -0.06
    .face
    -0.06
     Premiership
    -0.06
    POSITIVE LOGITS
    خل
    0.07
    .presentation
    0.07
     реак
    0.07
     увели
    0.07
                ↵            ↵
    0.07
     ό
    0.07
     Investig
    0.07
     environ
    0.07
    认识
    0.07
    (helper
    0.07
    Act Density 0.001%

    No Known Activations