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

    Neuronpedia

    INDEX
    Explanations

    TypeScript code components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     akibat
    0.46
     tepung
    0.40
    CompliancePolicy
    0.40
     vVertex
    0.39
     tonel
    0.38
     تكعيب
    0.38
     زیب
    0.38
    苎
    0.38
    ;,
    0.38
    Watercolor
    0.38
    POSITIVE LOGITS
     ALE
    0.41
     Mr
    0.40
     詳細
    0.39
    navbar
    0.38
     Ale
    0.38
     ale
    0.38
     ምስ
    0.38
    栞
    0.37
     GCBO
    0.36
    users
    0.36
    Act Density 0.002%

    No Known Activations