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

    Neuronpedia

    INDEX
    Explanations

    code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ڑ
    0.42
     vốn
    0.41
    accessible
    0.38
    issippi
    0.37
     постоянно
    0.37
     ColumnName
    0.37
     accessible
    0.36
     capital
    0.36
    ="./
    0.35
    fillna
    0.35
    POSITIVE LOGITS
     block
    1.09
     blok
    1.01
    block
    0.93
     блока
    0.91
     blocks
    0.90
     bloco
    0.89
    块
    0.89
     ब्लॉक
    0.88
     блок
    0.88
    blok
    0.87
    Act Density 0.045%

    No Known Activations