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

    Neuronpedia

    INDEX
    Explanations

    geek

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “Our
    -0.07
     télé
    -0.07
     Giáo
    -0.06
     dys
    -0.06
     traumat
    -0.06
    길
    -0.06
    朱
    -0.06
    COL
    -0.06
     wipes
    -0.06
    [Unit
    -0.06
    POSITIVE LOGITS
    ayacak
    0.07
     کیفیت
    0.06
    INCLUDING
    0.06
     overly
    0.06
     kromě
    0.06
     pomocí
    0.06
    间
    0.06
     использовани
    0.06
     цих
    0.06
     높은
    0.06
    Act Density 0.302%

    No Known Activations