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

    Neuronpedia

    INDEX
    Explanations

    technical terms and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.54
     Crem
    0.53
     Millie
    0.48
     Dispon
    0.47
     Sesame
    0.46
     Vibrant
    0.46
     Kraków
    0.46
     inoxydable
    0.45
     Din
    0.44
     Doyle
    0.44
    POSITIVE LOGITS
     잡아
    0.45
     группы
    0.44
    ifah
    0.43
    igel
    0.42
    ྐ
    0.42
    વાનું
    0.42
    itabbo
    0.42
     కలి
    0.41
    ωμα
    0.41
    눙
    0.41
    Act Density 0.003%

    No Known Activations