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

    Neuronpedia

    INDEX
    Explanations

    office structures and systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ench
    0.43
     sú
    0.39
     Sicherheits
    0.39
     updates
    0.38
     tans
    0.37
     Flug
    0.36
     Lumin
    0.36
     SDS
    0.35
     sodio
    0.35
    砂糖
    0.35
    POSITIVE LOGITS
    Bearer
    0.59
    Bear
    0.57
    bearers
    0.56
     bearer
    0.54
     Bear
    0.53
     bearers
    0.52
    bearer
    0.49
    bear
    0.47
     bear
    0.46
    Dust
    0.42
    Act Density 0.005%

    No Known Activations