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

    Neuronpedia

    INDEX
    Explanations

    yearbook message

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x0D>
    0.64
    ’
    0.64
    '
    0.63
    1
    0.62
    m
    0.57
    ↵
    0.56
      
    0.55
    </h3>
    0.52
    .
    0.52
     Demonstration
    0.51
    POSITIVE LOGITS
    мина
    0.66
     Paryayvachi
    0.66
    اریخ
    0.59
     despicable
    0.58
    が含ま
    0.56
    elevationMap
    0.56
    л
    0.56
     capucha
    0.55
    дите
    0.54
    лих
    0.54
    Act Density 0.000%

    No Known Activations