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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    μένου
    -0.07
    raising
    -0.07
    ‌کن
    -0.06
    رض
    -0.06
     않는
    -0.06
     DeV
    -0.06
     пользователя
    -0.06
     RELEASE
    -0.06
     Fraser
    -0.06
     passwords
    -0.06
    POSITIVE LOGITS
    ">&#
    0.07
     Ü
    0.07
     veget
    0.07
     디
    0.06
    .cid
    0.06
    -pre
    0.06
     вол
    0.06
     预
    0.06
     downside
    0.06
     baseURL
    0.06
    Act Density 0.012%

    No Known Activations