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

    Neuronpedia

    INDEX
    Explanations

    правильное, качественное, стабильное

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     गिवन
    0.35
     రోజుల
    0.34
     হৃদয়
    0.34
     wikipagina
    0.33
     vêtements
    0.33
     łyż
    0.32
     Stimme
    0.32
     potrav
    0.32
     woorden
    0.31
    碾
    0.31
    POSITIVE LOGITS
    <0xE3>
    0.32
    ’
    0.31
      
    0.29
    в
    0.29
    GR
    0.29
    :
    0.28
    чно
    0.28
    -
    0.27
    ное
    0.27
    с
    0.27
    Act Density 0.011%

    No Known Activations