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

    Neuronpedia

    INDEX
    Explanations

    lighthouses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jeans
    -0.09
     flavor
    -0.09
     flavored
    -0.09
    ilor
    -0.08
     idi
    -0.08
    花
    -0.08
    uria
    -0.08
     ingredient
    -0.08
     handbags
    -0.08
     salads
    -0.08
    POSITIVE LOGITS
     lighthouse
    0.15
     प्रहरी
    0.14
     stationed
    0.13
     Lighthouse
    0.12
     lookout
    0.11
     vigilancia
    0.11
     lonely
    0.11
     patrol
    0.10
    消防
    0.10
     Feuerwehr
    0.10
    Act Density 0.017%

    No Known Activations