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

    Neuronpedia

    INDEX
    Explanations

    brevity and simplification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    明明
    0.40
    гана
    0.39
     നല്ല
    0.38
     सक्षम
    0.38
    nocześnie
    0.38
     جيد
    0.37
     claros
    0.35
     secondly
    0.34
    另一方面
    0.34
     allowNull
    0.33
    POSITIVE LOGITS
     briefly
    1.01
     Briefly
    1.01
     brief
    0.85
    brief
    0.84
    Brief
    0.82
     brevity
    0.77
    略
    0.75
    simplified
    0.75
    省略
    0.75
     simplified
    0.74
    Act Density 0.011%

    No Known Activations