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

    Neuronpedia

    INDEX
    Explanations

    patches, store pages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Доб
    0.55
    мо
    0.51
    ту
    0.51
    Ро
    0.51
    ну
    0.49
    ک
    0.49
    Дан
    0.49
    М
    0.49
    of
    0.47
    так
    0.47
    POSITIVE LOGITS
     PubMed
    0.54
     Ceremon
    0.50
     നിൽ
    0.48
     Noronha
    0.48
     Utilizing
    0.47
     Iod
    0.47
     menstruation
    0.46
     permangan
    0.46
     hinder
    0.46
     vehement
    0.46
    Act Density 0.001%

    No Known Activations