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

    Neuronpedia

    INDEX
    Explanations

    registry keys and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fabric
    0.45
     vod
    0.45
     вод
    0.43
     water
    0.43
    WATER
    0.42
     fath
    0.42
     sand
    0.40
     Gers
    0.40
     水
    0.40
     वाटर
    0.40
    POSITIVE LOGITS
     Registry
    1.47
     registry
    1.43
    Registry
    1.35
    registry
    1.34
     registries
    1.15
     рее
    1.07
     रजिस्ट्री
    1.04
    reg
    0.99
     Reg
    0.95
    Reg
    0.94
    Act Density 0.014%

    No Known Activations