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

    Neuronpedia

    INDEX
    Explanations

    room, bedroom, chamber descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     [{\
    0.81
    zelfde
    0.76
     चलते
    0.73
     ({\
    0.70
     सहारे
    0.70
     taxing
    0.70
    टेगरी
    0.69
    mäßig
    0.69
     Polda
    0.67
     spus
    0.67
    POSITIVE LOGITS
     preoccupation
    0.89
    𝐢
    0.89
    装修
    0.86
    𝐌
    0.85
    Khal
    0.85
    Từ
    0.84
    卧室
    0.84
    bedrooms
    0.83
     upstairs
    0.82
    𝐍
    0.82
    Act Density 0.139%

    No Known Activations