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

    Neuronpedia

    INDEX
    Explanations

    UML class diagrams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     modeling
    0.47
     Modeling
    0.46
    预览
    0.46
     Modelling
    0.44
     MODEL
    0.43
     modelling
    0.43
    建模
    0.42
     Diagram
    0.41
     BEL
    0.40
     LEVEL
    0.40
    POSITIVE LOGITS
     UnwrapRef
    0.43
    unordered
    0.40
     waved
    0.38
    ہر
    0.37
    וק
    0.37
    लिब्र
    0.37
    cPix
    0.37
    orderLine
    0.37
    ⃖
    0.36
    求め
    0.35
    Act Density 0.005%

    No Known Activations