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

    Neuronpedia

    INDEX
    Explanations

    "along" or foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     তোম
    -0.08
     అంటే
    -0.07
     yelled
    -0.07
    nid
    -0.07
    Ant
    -0.07
     sonrası
    -0.07
     تغي
    -0.07
    .change
    -0.07
    Complex
    -0.07
    .TEST
    -0.07
    POSITIVE LOGITS
     entlang
    0.15
    沿
    0.15
     לאורך
    0.13
     sepanjang
    0.12
     boyunca
    0.12
    长度
    0.10
    線
    0.10
     shoreline
    0.10
     лини
    0.10
    线
    0.10
    Act Density 0.053%

    No Known Activations