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

    Neuronpedia

    INDEX
    Explanations

    place names and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Riemannian
    0.51
     nonzero
    0.49
     Kolmogorov
    0.43
     Hubble
    0.41
     MacOS
    0.41
     BatchNorm
    0.40
     Simplify
    0.40
     Srivastava
    0.40
     PlayerSelector
    0.39
     cardinality
    0.39
    POSITIVE LOGITS
     Gardens
    0.72
     Creek
    0.68
     gardens
    0.66
     Park
    0.64
    Park
    0.61
     Plaza
    0.58
     park
    0.57
     Cove
    0.56
     Avenue
    0.55
     Grove
    0.55
    Act Density 0.041%

    No Known Activations