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

    Neuronpedia

    INDEX
    Explanations

    emphasizes the quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    0.59
     development
    0.50
     including
    0.49
     procedures
    0.48
     equipment
    0.48
    development
    0.47
     International
    0.46
     Equipment
    0.46
     to
    0.45
     address
    0.45
    POSITIVE LOGITS
    󰀄
    0.59
     दट
    0.54
     የበለጠ
    0.52
    Energie
    0.52
     percepción
    0.52
     pInBuffer
    0.51
    Vaterpolo
    0.51
    Methylsulfanyl
    0.51
    istič
    0.50
     сильнее
    0.49
    Act Density 0.014%

    No Known Activations