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

    Neuronpedia

    INDEX
    Explanations

    concepts and progress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gigantic
    0.44
     Physical
    0.38
     Many
    0.38
     bijna
    0.37
     soltanto
    0.37
     strlen
    0.36
     tất
    0.36
     innumerable
    0.35
     indispensable
    0.35
     unprecedented
    0.35
    POSITIVE LOGITS
     טוב
    0.47
    р
    0.45
    คุณภาพ
    0.45
     போன்றவை
    0.44
    Denne
    0.44
    😊
    0.44
     интересный
    0.41
    humidité
    0.40
     jakości
    0.40
    Retour
    0.40
    Act Density 0.050%

    No Known Activations