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

    Neuronpedia

    INDEX
    Explanations

    shopping

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oling
    -0.27
     widespread
    -0.27
    id
    -0.26
    æĭĽçĶŁ
    -0.25
    æµģ
    -0.25
    æݨ
    -0.25
    wij
    -0.24
    idue
    -0.24
     Classroom
    -0.24
    enz
    -0.24
    POSITIVE LOGITS
     ratios
    0.26
    è·½
    0.26
    ä¹°åĪ°
    0.25
    好åIJĹ
    0.25
    erus
    0.24
    ,[],
    0.24
    .removeAttribute
    0.23
     shuttle
    0.23
    quat
    0.23
     express
    0.23
    Act Density 0.004%

    No Known Activations