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

    Neuronpedia

    INDEX
    Explanations

    pounds weight comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InstrumentedTest
    0.39
    жень
    0.38
    لاسه
    0.38
     पासवान
    0.37
    まって
    0.37
    藠
    0.36
     parum
    0.36
    탐
    0.36
     পৰ
    0.35
     ትንሽ
    0.35
    POSITIVE LOGITS
    GBP
    0.41
    daad
    0.41
     EPL
    0.40
     PML
    0.40
    ุน
    0.40
     lighter
    0.40
    submitted
    0.40
     Shannon
    0.39
    ">$
    0.39
     £
    0.38
    Act Density 0.000%

    No Known Activations