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

    Neuronpedia

    INDEX
    Explanations

    disturbance and control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Architecture
    0.98
     Architecture
    0.82
    架构
    0.80
    Brick
    0.79
    Endian
    0.78
    architecture
    0.78
     Architektur
    0.77
     worldRank
    0.77
    Architect
    0.77
     NUCLEAR
    0.75
    POSITIVE LOGITS
     disturbance
    1.33
     disturb
    1.15
     crews
    1.13
     disturbing
    1.12
     disturbed
    1.08
     disturbances
    1.05
     disturbs
    1.03
     vegetation
    1.02
    disturbance
    1.01
     depred
    0.96
    Act Density 0.116%

    No Known Activations