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

    Neuronpedia

    INDEX
    Explanations

    permissions or instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     добре
    -0.07
     Kills
    -0.07
    щини
    -0.07
    965
    -0.07
     RNA
    -0.06
     rubbing
    -0.06
    ，从
    -0.06
     Obesity
    -0.06
     iid
    -0.06
     Rub
    -0.06
    POSITIVE LOGITS
    }))↵↵
    0.07
    σιεύ
    0.06
    .AutoScale
    0.06
    (correct
    0.06
    tere
    0.06
    Scaling
    0.06
    cassert
    0.06
     nướng
    0.06
    Cart
    0.06
     agr
    0.06
    Act Density 0.001%

    No Known Activations