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

    Neuronpedia

    INDEX
    Explanations

    places and activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ier
    0.81
    onomi
    0.80
    encial
    0.79
    ile
    0.73
    ü
    0.73
    ithmet
    0.72
    \
    0.71
    cc
    0.70
    end
    0.69
    ulative
    0.69
    POSITIVE LOGITS
     caves
    1.52
     Dinosaur
    1.45
     Caves
    1.44
     vineyards
    1.43
     wetlands
    1.43
     Cemetery
    1.40
     wineries
    1.40
     Lake
    1.40
     waterfalls
    1.39
     museums
    1.39
    Act Density 0.729%

    No Known Activations