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

    Neuronpedia

    INDEX
    Explanations

    person, role, age, or specification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dataIn
    0.41
    জাতি
    0.37
    মানে
    0.37
     Gazetteer
    0.37
     ऐप्स
    0.36
    ⟫
    0.36
     düny
    0.35
    ]))
    0.35
    enial
    0.35
     jurisdict
    0.35
    POSITIVE LOGITS
     another
    0.37
     서
    0.36
     दूसरा
    0.34
     medium
    0.34
     listener
    0.33
     तीसरे
    0.33
    5
    0.33
     Chu
    0.32
     lavender
    0.32
    螢
    0.32
    Act Density 0.160%

    No Known Activations