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

    Neuronpedia

    INDEX
    Explanations

    license and disclaimer text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    burne
    0.92
    adecimal
    0.90
     nCount
    0.90
    melee
    0.89
     века
    0.89
    leszt
    0.88
     millió
    0.88
    IMUM
    0.86
    ayaran
    0.85
     চুলের
    0.85
    POSITIVE LOGITS
     urlpatterns
    0.78
    并通过
    0.77
     cum
    0.75
     umbrella
    0.72
     osp
    0.72
     updated
    0.71
     dune
    0.70
     #
    0.70
    フォーム
    0.69
     dex
    0.69
    Act Density 0.001%

    No Known Activations