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

    Neuronpedia

    INDEX
    Explanations

    broken appliances or devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Leveraging
    0.45
     Labrenzia
    0.45
     leveraging
    0.42
     leveraged
    0.41
     topologies
    0.40
     چاہی
    0.39
     ډول
    0.39
     leverages
    0.38
    颧
    0.38
     prepd
    0.37
    POSITIVE LOGITS
     malfunctioning
    1.97
     malfunction
    1.72
     malfunctions
    1.66
     작동
    1.44
    故障
    1.42
     faulty
    1.29
     defective
    1.26
     dysfunctional
    1.22
     functioning
    1.16
     funktionieren
    1.16
    Act Density 0.025%

    No Known Activations