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

    Neuronpedia

    INDEX
    Explanations

    dates and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     온도
    0.31
     आत्मा
    0.31
     oth
    0.31
     সম্মত
    0.31
     giây
    0.30
    過程
    0.30
     groupBox
    0.30
     सुरक्षा
    0.29
     사람이
    0.29
     과정
    0.29
    POSITIVE LOGITS
    .
    0.57
    ↵
    0.49
    년
    0.48
    -
    0.47
    /
    0.44
    ↵↵
    0.42
    ,
    0.42
     yılında
    0.41
    年
    0.40
     silam
    0.40
    Act Density 0.089%

    No Known Activations