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

    Neuronpedia

    INDEX
    Explanations

    countries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    result
    -0.07
    　　　 　 　 　
    -0.07
     print
    -0.07
    LEM
    -0.07
    يفة
    -0.07
    dealer
    -0.07
     meme
    -0.06
    　　　　　 　
    -0.06
     المللی
    -0.06
     substring
    -0.06
    POSITIVE LOGITS
     вищ
    0.06
     pod
    0.06
    .TabStop
    0.06
    irate
    0.06
    .fromString
    0.06
     Milit
    0.06
     Nova
    0.05
     dors
    0.05
     htt
    0.05
    ][$
    0.05
    Act Density 0.019%

    No Known Activations