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

    Neuronpedia

    INDEX
    Explanations

    Amsterdam, historic dam, windmills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Belgium
    0.75
    Belgium
    0.73
     Flemish
    0.68
     Belgian
    0.68
     Antwerp
    0.63
     belg
    0.62
     Bruges
    0.59
     Belgien
    0.57
     Belgi
    0.55
     Flanders
    0.55
    POSITIVE LOGITS
     እድ
    0.38
     توسعه
    0.37
     retaining
    0.35
    체의
    0.35
    ControlType
    0.35
    体の
    0.35
    δήποτε
    0.34
     ausp
    0.34
    خصة
    0.34
     அபி
    0.34
    Act Density 0.006%

    No Known Activations