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

    Neuronpedia

    INDEX
    Explanations

    simplifying equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وګ
    0.50
     terj
    0.43
     سک
    0.42
     numar
    0.40
    নিং
    0.40
     ну
    0.39
     मानो
    0.39
     datap
    0.39
     tanya
    0.39
     fundamento
    0.38
    POSITIVE LOGITS
    anskrit
    0.45
     मंत्रिमंडल
    0.45
    াড়
    0.44
    oxins
    0.40
    🔯
    0.40
     एपिस
    0.39
    ଉ
    0.39
     Notation
    0.38
     Ontology
    0.38
    an
    0.37
    Act Density 0.013%

    No Known Activations