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

    Neuronpedia

    INDEX
    Explanations

    living room

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    論
    0.42
    ాగ
    0.42
    GRU
    0.41
     giriyoruz
    0.39
    iquement
    0.38
    emente
    0.38
     bois
    0.38
    lives
    0.37
     bahagia
    0.37
    слен
    0.37
    POSITIVE LOGITS
     Living
    0.54
    Living
    0.52
     LIVING
    0.52
     प्राणियों
    0.49
    wage
    0.48
     Wage
    0.47
     organisms
    0.46
    ROOM
    0.46
    room
    0.46
     wage
    0.45
    Act Density 0.006%

    No Known Activations