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

    Neuronpedia

    INDEX
    Explanations

    further fuels increase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     använda
    1.01
     रहना
    0.87
     använder
    0.87
     considerare
    0.86
     vannak
    0.85
     знать
    0.84
     spends
    0.84
    中使用
    0.84
     usar
    0.83
    Examination
    0.83
    POSITIVE LOGITS
     enhance
    2.35
     enhances
    2.31
     increase
    2.20
     reduce
    2.12
     reduces
    2.10
     improve
    2.02
     meningkatkan
    1.98
     improves
    1.96
     enhancing
    1.89
     zwięks
    1.86
    Act Density 0.734%

    No Known Activations