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

    Neuronpedia

    INDEX
    Explanations

    rooms and spaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inger
    0.75
     விகி
    0.73
    ulative
    0.72
    owanych
    0.72
     정책
    0.72
     miRNAs
    0.72
    oviruses
    0.72
     배워
    0.71
    ympt
    0.71
     scalar
    0.70
    POSITIVE LOGITS
     hallway
    2.21
     courtyard
    2.20
     rooms
    2.15
     hallways
    2.10
     bedroom
    2.10
     room
    2.03
     auditorium
    1.99
     apartment
    1.99
     hangar
    1.85
    房间
    1.84
    Act Density 0.723%

    No Known Activations