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

    Neuronpedia

    INDEX
    Explanations

    spaces and properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    房子
    0.77
    ुअल
    0.77
     buildings
    0.73
    房地产
    0.73
    Building
    0.72
     Building
    0.72
     premises
    0.72
     yearly
    0.72
    Property
    0.71
     déprim
    0.71
    POSITIVE LOGITS
     mixed
    1.04
     Mixed
    0.95
     operable
    0.90
    Mixed
    0.88
    mixed
    0.84
     adaptive
    0.78
    Amen
    0.77
     Amen
    0.77
     podium
    0.76
     shared
    0.75
    Act Density 0.094%

    No Known Activations