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

    Neuronpedia

    INDEX
    Explanations

    inspection and costs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lic
    0.42
    <!---
    0.42
    照顧
    0.42
     TRE
    0.41
     лицен
    0.40
    തോ
    0.39
     Lic
    0.39
     STRA
    0.39
    照顾
    0.38
     licenc
    0.38
    POSITIVE LOGITS
     Inspectors
    0.52
     inspectors
    0.49
     inspector
    0.47
     Inspector
    0.45
    inspector
    0.45
     costs
    0.42
    pesas
    0.41
     inspection
    0.40
     skyscrapers
    0.40
    Inspector
    0.40
    Act Density 0.003%

    No Known Activations