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

    Neuronpedia

    INDEX
    Explanations

    bloomberg gutenberg sternberg

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bur
    1.24
     bur
    1.20
    Bur
    1.16
    BUR
    1.07
     бур
    1.04
     BUR
    1.02
     Burr
    1.00
     burrito
    0.95
    bur
    0.92
     Burs
    0.86
    POSITIVE LOGITS
    berg
    1.95
     berg
    1.95
    Berg
    1.92
     Berg
    1.87
    BERG
    1.86
    берг
    1.68
    bergs
    1.53
    enberg
    1.30
     Bergman
    1.27
    sberg
    1.03
    Act Density 0.004%

    No Known Activations