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

    Neuronpedia

    INDEX
    Explanations

    primary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wyn
    -0.08
    竣
    -0.07
    Lane
    -0.07
    ⋱
    -0.07
     למנ
    -0.07
     Assoc
    -0.07
     startPos
    -0.07
    ivia
    -0.07
     пен
    -0.07
    节水
    -0.07
    POSITIVE LOGITS
    进行了
    0.08
    кой
    0.08
     underestimated
    0.08
    .gpu
    0.07
     Similar
    0.07
    ими
    0.07
    _Global
    0.07
    是在
    0.07
    ada
    0.07
     mirrored
    0.07
    Act Density 0.006%

    No Known Activations