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

    Neuronpedia

    INDEX
    Explanations

    places, homes, workshops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nä
    0.66
     resa
    0.59
    Liste
    0.59
     świet
    0.57
    党的
    0.56
     Setter
    0.56
    据悉
    0.55
    身上
    0.55
     svijet
    0.55
    ો
    0.55
    POSITIVE LOGITS
    mates
    0.90
    rooms
    0.80
    credits
    0.78
    entos
    0.75
    ROOM
    0.75
    buildings
    0.74
    вав
    0.73
    ohms
    0.72
    ঘর
    0.71
    voices
    0.71
    Act Density 1.475%

    No Known Activations