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

    Neuronpedia

    INDEX
    Explanations

    Full lifecycle, healthcare, hops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Embedded
    0.42
    nable
    0.38
    iable
    0.38
     Ceramic
    0.38
    able
    0.37
     States
    0.37
     PRE
    0.36
     Ceramics
    0.36
     Officer
    0.36
     Notable
    0.36
    POSITIVE LOGITS
    ாதார
    0.46
    ষ্ঠান
    0.45
    Westinghouse
    0.43
    гро
    0.41
    သောအ
    0.41
    StarGo
    0.41
    舘
    0.41
     冖
    0.41
     monoc
    0.40
    Retour
    0.40
    Act Density 0.001%

    No Known Activations