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

    Neuronpedia

    INDEX
    Explanations

    recipe ingredients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    utors
    0.44
     Cooling
    0.43
     Kinetics
    0.43
     mentoring
    0.41
     Kanpur
    0.41
     Hrs
    0.40
     cooling
    0.39
     hosting
    0.39
     Kö
    0.38
     Überg
    0.38
    POSITIVE LOGITS
    on
    0.50
     asegur
    0.48
    Paulo
    0.48
    还
    0.48
    스는
    0.46
    िनय
    0.46
    ס
    0.45
    ສາມາດ
    0.45
    最终
    0.44
    스로
    0.44
    Act Density 0.003%

    No Known Activations