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

    Neuronpedia

    INDEX
    Explanations

    compatible API, yoga experience, Law, figure, inclusivity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     paralelas
    0.53
     oblik
    0.49
     plastik
    0.45
     effluents
    0.45
     plast
    0.44
     трубы
    0.44
     searchText
    0.44
     пласти
    0.44
     oblic
    0.44
     obstruct
    0.44
    POSITIVE LOGITS
     Gear
    0.53
     Moines
    0.48
     Hits
    0.48
    Gear
    0.48
     Hike
    0.46
     Delaware
    0.46
    už
    0.45
     Mā
    0.45
    emaker
    0.44
     Sioux
    0.44
    Act Density 0.002%

    No Known Activations